MA(1)
In Table 4 , the parameter estimates for the best models are presented. The fitted and predicted values are presented in Figure 2 . As seen in Table 5 for both software, the next two weeks estimate of confirmed cases may be between 2450.74–5673.29, 12,616.5–16,896.3, 19,400.9–21,280.5, 27,404.9–32,340.9, 52,247.6–75,717.2, 88,483.4–103,777, 88,427.4–101,440, respectively through STATGRAPHICS Centurion (v.18.1.13). For IBM SPSS (v.20.0.0), the forecast for the next two weeks is as follows: 2478.78–6715.00, 12,599.76–16,756.08, 19,412.18–21,910.55, 27,405.69–33,181.42, 52,168.29–67,467.42, 88,444.38–103,059.41, and 88,451.83–102,656.81 for March, April, May, June, July, August, and March–August.
Time-series plots for the best ARIMA models through ( a ) STATGRAPHICS Centurion (v.18.1.13) and ( b ) IBM SPSS (v.20.0.0).
Prediction of total confirmed cases of COVID−19 for the next two weeks through ( a ) STATGRAPHICS Centurion (v.18.1.13) and ( b ) IBM SPSS (v.20.0.0).
01-4-20 | 2450.74 | 2368.24 | 2533.23 | ||||
02-4-20 | 2732.0 | 2593.82 | 2870.18 | ||||
03-4-20 | 2947.89 | 2716.13 | 3179.66 | ||||
04-4-20 | 3220.37 | 2900.32 | 3540.42 | ||||
05-4-20 | 3443.87 | 3011.65 | 3876.09 | ||||
06-4-20 | 3709.76 | 3166.05 | 4253.47 | ||||
07-4-20 | 3938.96 | 3266.6 | 4611.32 | ||||
08-4-20 | 4199.91 | 3397.23 | 5002.6 | ||||
09-4-20 | 4433.39 | 3487.15 | 5379.63 | ||||
10-4-20 | 4690.65 | 3597.86 | 5783.43 | ||||
11-4-20 | 4927.32 | 3677.29 | 6177.34 | ||||
12-4-20 | 5181.81 | 3770.81 | 6592.81 | ||||
13-4-20 | 5420.88 | 3839.91 | 7001.84 | ||||
14-4-20 | 5673.29 | 3918.22 | 7428.36 | ||||
01-5-20 | 12,616.5 | 12,440.4 | 12,792.5 | ||||
02-5-20 | 12,959.9 | 12,738.5 | 13,181.4 | ||||
03-5-20 | 13,302.9 | 13,061.4 | 13,544.4 | ||||
04-5-20 | 13,615.5 | 13,368.8 | 13,862.3 | ||||
05-5-20 | 13,932.3 | 13,674.7 | 14,189.9 | ||||
06-5-20 | 14,257.0 | 13,975.5 | 14,538.5 | ||||
07-5-20 | 14,592.6 | 14,276.6 | 14,908.7 | ||||
08-5-20 | 14,927.5 | 14,579.7 | 15,275.3 | ||||
09-5-20 | 15,257.2 | 14,883.3 | 15,631.0 | ||||
10-5-20 | 15,582.2 | 15,184.3 | 15,980.1 | ||||
11-5-20 | 15,907.6 | 15,482.8 | 16,332.4 | ||||
12-5-20 | 16,235.9 | 15,779.8 | 16,692.0 | ||||
13-5-20 | 16,566.2 | 16,076.4 | 17,056.0 | ||||
14-5-20 | 16,896.3 | 16,372.8 | 17,419.8 | ||||
01-6-20 | 19,400.9 | 19,280.2 | 19,521.5 | ||||
02-6-20 | 19,533.0 | 19,286.3 | 19,779.8 | ||||
03-6-20 | 19,689.2 | 19,296.5 | 20,081.9 | ||||
04-6-20 | 19,831.8 | 19,307.7 | 20,355.9 | ||||
05-6-20 | 19,971.4 | 19,290.8 | 20,651.9 | ||||
06-6-20 | 20,122.2 | 19,270.7 | 20,973.7 | ||||
07-6-20 | 20,265.2 | 19,240.9 | 21,289.5 | ||||
08-6-20 | 20,408.1 | 19,194.8 | 21,621.5 | ||||
09-6-20 | 20,556.2 | 19,143.4 | 21,968.9 | ||||
10-6-20 | 20,699.9 | 19,081.8 | 22,318.0 | ||||
11-6-20 | 20,844.3 | 19,009.0 | 22,679.7 | ||||
12-6-20 | 20,991.0 | 18,929.9 | 23,052.1 | ||||
13-6-20 | 21,135.4 | 18,841.3 | 23,429.4 | ||||
14-6-20 | 21,280.5 | 18,744.1 | 23,816.9 | ||||
01-7-20 | 27,404.9 | 27,291.5 | 27,518.3 | ||||
02-7-20 | 27,860.4 | 27,673.0 | 28,047.7 | ||||
03-7-20 | 28,267.6 | 28,019.4 | 28,515.8 | ||||
04-7-20 | 28,608.4 | 28,307.9 | 28,908.9 | ||||
05-7-20 | 28,916.8 | 28,551.9 | 29,281.8 | ||||
06-7-20 | 29,253.3 | 28,792.0 | 29,714.6 | ||||
07-7-20 | 29,652.8 | 29,060.9 | 30,244.7 | ||||
08-7-20 | 30,097.5 | 29,360.4 | 30,834.6 | ||||
09-7-20 | 30,533.1 | 29,658.3 | 31,407.9 | ||||
10-7-20 | 30,914.6 | 29,916.3 | 31,912.9 | ||||
11-7-20 | 31,243.0 | 30,126.4 | 32,359.6 | ||||
12-7-20 | 31,562.8 | 30,317.0 | 32,808.5 | ||||
13-7-20 | 31,924.0 | 30,526.8 | 33,321.1 | ||||
14-7-20 | 32,340.9 | 30,772.3 | 33,909.5 | ||||
01-8-20 | 52,247.6 | 51,999.2 | 52,496.1 | ||||
02-8-20 | 53,668.7 | 53,169.6 | 54,167.9 | ||||
03-8-20 | 55,147.3 | 54,390.9 | 55,903.6 | ||||
04-8-20 | 56,685.2 | 55,656.5 | 57,714.0 | ||||
05-8-20 | 58,282.6 | 56,976.8 | 59,588.5 | ||||
06-8-20 | 59,942.3 | 58,346.7 | 61,537.9 | ||||
07-8-20 | 61,665.3 | 59,772.1 | 63,558.4 | ||||
08-8-20 | 63,454.6 | 61,250.0 | 65,659.3 | ||||
09-8-20 | 65,311.9 | 62,784.7 | 67,839.2 | ||||
10-8-20 | 67,240.4 | 64,374.9 | 70,106.0 | ||||
11-8-20 | 69,242.1 | 66,024.5 | 72,459.8 | ||||
12-8-20 | 71,320.4 | 67,733.2 | 74,907.6 | ||||
13-8-20 | 73,477.6 | 69,504.9 | 77,450.3 | ||||
14-8-20 | 75,717.2 | 71,340.0 | 80,094.4 | ||||
01-9-20 | 88,483.4 | 88,163.3 | 88,803.4 | ||||
02-9-20 | 89,735.8 | 89,186.2 | 90,285.4 | ||||
03-9-20 | 91,171.6 | 90,521.1 | 91,822.0 | ||||
04-9-20 | 92,553.1 | 91,883.1 | 93,223.0 | ||||
05-9-20 | 93,723.4 | 93,050.4 | 94,396.4 | ||||
06-9-20 | 94,707.0 | 94,020.1 | 95,393.9 | ||||
07-9-20 | 95,660.3 | 94,899.8 | 96,420.7 | ||||
08-9-20 | 96,734.6 | 95,825.9 | 97,643.3 | ||||
09-9-20 | 97,966.8 | 96,901.4 | 99,032.2 | ||||
10-9-20 | 99,272.2 | 98,093.1 | 100,451. | ||||
11-9-20 | 100,527. | 99,273.2 | 101,781. | ||||
12-9-20 | 101,667. | 100,347. | 102,986. | ||||
13-9-20 | 102,721. | 101,316. | 104,126. | ||||
14-9-20 | 103,777. | 102,249. | 105,305. | ||||
01-9-20 | 88,427.4 | 88,187.3 | 88,667.5 | ||||
02-9-20 | 89,378.4 | 88,905.1 | 89,851.7 | ||||
03-9-20 | 90,359.9 | 89,641.2 | 91,078.7 | ||||
04-9-20 | 91,356.1 | 90,382.1 | 92,330.1 | ||||
05-9-20 | 92,359.3 | 91,120.4 | 93,598.2 | ||||
06-9-20 | 93,365.8 | 91,851.8 | 94,879.9 | ||||
07-9-20 | 94,374.0 | 92,574.3 | 96,173.7 | ||||
08-9-20 | 95,383.0 | 93,286.8 | 97,479.2 | ||||
09-9-20 | 96,392.3 | 93,988.7 | 98,796.0 | ||||
10-9-20 | 97,401.8 | 94,679.8 | 100,124. | ||||
11-9-20 | 98,411.4 | 95,360.3 | 101,463. | ||||
12-9-20 | 99,421.1 | 96,030.1 | 102,812. | ||||
13-9-20 | 100,431. | 96,689.5 | 104,172. | ||||
14-9-20 | 101,440. | 97,338.6 | 105,542. | ||||
Model | |||||||
Cumulative-Model (March) | Forecast | 2478.78 | 2771.81 | 3036.46 | 3337.56 | 3627.14 | 3940.69 |
UCL | 2557.11 | 2895.56 | 3237.39 | 3612.37 | 3992.87 | 4399.42 | |
LCL | 2400.44 | 2648.06 | 2835.53 | 3062.74 | 3261.42 | 3481.96 | |
Model | |||||||
Cumulative-Model (March) | Forecast | 4251.96 | 4580.37 | 4911.55 | 5256.13 | 5606.25 | 5967.72 |
UCL | 4814.73 | 5251.20 | 5698.58 | 6164.03 | 6641.61 | 7135.33 | |
LCL | 3689.20 | 3909.55 | 4124.53 | 4348.24 | 4570.89 | 4800.11 | |
Model | |||||||
Cumulative-Model (March) | Forecast | 6336.24 | 6715.00 | ||||
UCL | 7641.78 | 8163.17 | |||||
LCL | 5030.71 | 5266.84 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (April) | Forecast | 12,599.76 | 12,935.87 | 13,271.55 | 13,584.87 | 13,898.80 | 14,216.66 |
UCL | 12,774.44 | 13,150.93 | 13,500.98 | 13,816.96 | 14,136.69 | 14,467.65 | |
LCL | 12,425.08 | 12,720.81 | 13,042.12 | 13,352.78 | 13,660.91 | 13,965.67 | |
Model | |||||||
Cumulative-Model (April) | Forecast | 14,540.05 | 14,862.45 | 15,181.23 | 15,496.84 | 15,811.68 | 16,126.86 |
UCL | 14,808.71 | 15,145.84 | 15,475.55 | 15,800.64 | 16,125.74 | 16,452.34 | |
LCL | 14,271.39 | 14,579.05 | 14,886.92 | 15,193.03 | 15,497.61 | 15,801.38 | |
Model | |||||||
Cumulative-Model (April) | Forecast | 16,441.99 | 16,756.08 | ||||
UCL | 16,779.10 | 17,104.18 | |||||
LCL | 16,104.88 | 16,407.98 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (May) | Forecast | 19,412.18 | 19,569.68 | 19,763.17 | 19,935.78 | 20,118.83 | 20,313.78 |
UCL | 19,543.30 | 19,816.82 | 20,130.38 | 20,397.32 | 20,688.05 | 20,989.84 | |
LCL | 19,281.05 | 19,322.54 | 19,395.96 | 19,474.23 | 19,549.62 | 19,637.71 | |
Model | |||||||
Cumulative-Model (May) | Forecast | 20,501.17 | 20,696.67 | 20,895.88 | 21,093.45 | 21,295.88 | 21,499.60 |
UCL | 21,277.17 | 21,576.47 | 21,877.30 | 22,173.28 | 22,473.47 | 22,773.08 | |
LCL | 19,725.17 | 19,816.88 | 19,914.45 | 20,013.63 | 20,118.28 | 20,226.12 | |
Model | |||||||
Cumulative-Model (May) | Forecast | 21,703.75 | 21,910.55 | ||||
UCL | 23,071.27 | 23,369.65 | |||||
LCL | 20,336.23 | 20,451.44 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (June) | Forecast | 27,405.69 | 27,851.25 | 28,248.97 | 28,627.75 | 29,018.52 | 29,447.71 |
UCL | 27,520.95 | 28,038.23 | 28,481.50 | 28,874.60 | 29,273.56 | 29,714.32 | |
LCL | 27,290.42 | 27,664.28 | 28,016.44 | 28,380.90 | 28,763.48 | 29,181.10 | |
Model | |||||||
Cumulative-Model (June) | Forecast | 29,901.63 | 30,359.87 | 30,809.40 | 31,257.55 | 31,716.79 | 32,193.86 |
UCL | 30,190.48 | 30,674.74 | 31,145.84 | 31,609.14 | 32,081.24 | 32,572.50 | |
LCL | 29,612.78 | 30,045.00 | 30,472.95 | 30,905.96 | 31,352.35 | 31,815.21 | |
Model | |||||||
Cumulative-Model (June) | Forecast | 32,684.53 | 33,181.42 | ||||
UCL | 33,079.98 | 33,594.43 | |||||
LCL | 32,289.08 | 32,768.41 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (July) | Forecast | 52,168.29 | 53,426.67 | 54,674.30 | 55,902.11 | 57,118.49 | 58,317.76 |
UCL | 52,449.73 | 54,031.51 | 55,633.07 | 57,264.85 | 58,911.15 | 60,573.52 | |
LCL | 51,886.84 | 52,821.82 | 53,715.54 | 54,539.37 | 55,325.84 | 56,061.99 | |
Model | |||||||
Cumulative-Model (July) | Forecast | 59,505.46 | 60,678.11 | 61,839.43 | 62,987.33 | 64,124.34 | 65,249.25 |
UCL | 62,244.36 | 63,923.34 | 65,606.40 | 67,292.68 | 68,979.84 | 70,666.96 | |
LCL | 56,766.56 | 57,432.88 | 58,072.46 | 58,681.98 | 59,268.84 | 59,831.54 | |
Model | |||||||
Cumulative-Model (July) | Forecast | 66,363.83 | 67,467.42 | ||||
UCL | 72,352.60 | 74,035.96 | |||||
LCL | 60,375.05 | 60,898.88 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (August) | Forecast | 88,444.38 | 89,634.01 | 91,015.67 | 92,372.04 | 93,537.29 | 94,506.51 |
UCL | 88,730.43 | 90,079.75 | 91,493.00 | 92,852.85 | 94,048.38 | 95,027.52 | |
LCL | 88,158.32 | 89,188.27 | 90,538.35 | 91,891.23 | 93,026.19 | 93,985.50 | |
Model | |||||||
Cumulative-Model (August) | Forecast | 95,412.10 | 96,406.37 | 97,549.71 | 98,783.13 | 99,990.33 | 101,090.16 |
UCL | 95,938.80 | 96,978.64 | 98,171.45 | 99,421.94 | 100,629.11 | 101,728.19 | |
LCL | 94,885.41 | 95,834.09 | 96,927.97 | 98,144.32 | 99,351.54 | 100,452.13 | |
Model | |||||||
Cumulative-Model (August) | Forecast | 102,088.51 | 103,059.41 | ||||
UCL | 102,726.16 | 103,708.74 | |||||
LCL | 101,450.85 | 102,410.08 | |||||
Forecast | |||||||
Model | |||||||
Cumulative-Model (March–August) | Forecast | 88,451.83 | 89,445.12 | 90,482.12 | 91,543.96 | 92,621.15 | 93,708.98 |
UCL | 88,690.71 | 89,912.30 | 91,185.57 | 92,489.10 | 93,813.54 | 95,154.94 | |
LCL | 88,212.96 | 88,977.94 | 89,778.67 | 90,598.81 | 91,428.77 | 92,263.03 | |
Model | |||||||
Cumulative-Model (March–August) | Forecast | 94,805.08 | 95,908.24 | 97,017.89 | 98,133.72 | 99,255.59 | 100,383.41 |
UCL | 96,511.68 | 97,883.14 | 99,269.09 | 100,669.45 | 102,084.15 | 103,513.14 | |
LCL | 93,098.47 | 93,933.34 | 94,766.69 | 95,598.00 | 96,427.02 | 97,253.68 | |
Model | |||||||
Cumulative-Model (March–August) | Forecast | 101,517.16 | 102,656.81 | ||||
UCL | 104,956.35 | 106,413.66 | |||||
LCL | 98,077.97 | 98,899.95 |
Regarding the mortality rate, since 11 June until 31 August a total of 2261 patients were identified, from which 1356 (59.97%) were male and 905 (40.02%) were female. The most affected age group were people aged between 70 and 79 years, where SARS-CoV-2 caused the death of 709 people, followed by people between 60 and 69 years with 621 deaths and >80 with 526 deaths ( Figure 3 ). On the other hand, a total of 405 people died, from which 260 had between 50 and 59 years, 104 between 40 and 49 years, 30 between 30 and 39 years, 10 between 20 and 29 years, 1 between 10 and 19 years, and 0 with less than 10 years old. From the total number of 2261 people, 2184 had comorbidities (96.6823%), and 77 not. As well, since 17 March when the first 4 people were confirmed, the total number registered until 31 August was 506 ( Figure 4 ).
The number of deaths depending on the age group.
The total number of patients hospitalized in ICU.
Based on our results, it can be concluded that Romania will face an even higher number of infections which can exceed one hundred thousand. In terms of the number of deaths, these figures are not comparable with other countries such as Italy, Spain, or France. The probability of exceeding 1000 is very small, especially due to the high longevity rate of people from other states compared to Romania.
According to the current literature, this is the first study of such a manner. Thus, the idea of testing the accuracy of the ARIMA model using two distinct statistical software is novel, all the more so as middle-class countries do not have the resources necessary or a reliable strategy in restraining the rate of contagion or transmissibility in such conditions. For an unknown reason, most studies have focused on Westernized or China’s neighboring countries.
Recently, a team of authors proposed three new methods for studying the epidemiological course of COVID-19. The first one is a universal physics-based model designed to assess the COVID-19 dynamics in Europe. The model folds within the existing curve due to the fact that the results obtained following simulation indicate an evolution curve related to that describing the current status. This “overlap” can be explained by the fact that this approach is based on a universal mechanism, having as a structural concept, the “diffusion over a lattice”. In this context, it has been successfully applied for seven European countries, and further offers the chance to study the memory effects through autocorrelation within the epidemiological dynamical systems [ 22 ]. Furthermore, Demertzis et al. [ 23 ] applied an exploratory time-series analysis built on a recent conceptualization. More specific, is dedicated in detecting connective communities by developing a novel spline regression in which the knot vector is represented by the community detection in a complex network. Through this approach, the authors demonstrated the reliability of this exploratory time-series analysis in decision-making in Greece, mainly because diagnostic testing, services, and resources strategies vary between countries. Finally, Tsiotas et al. [ 24 ] used the modularity optimization algorithm in which the visibility graphs generated describe a sequence of different typologies that this disease has. According to their results, the current pandemic in Greece is about to reach the second half in a decreasing manner, whereas the chances for a “maximum infection” are low due to the saturation point reached.
Quarantine is the first alternative, Chintalapudi et al. [ 25 ] demonstrated that in Italy this approach promoted a reduction up to 35% of the total registered cases, in parallel with a significant percentage (66%) of recovered cases.
Considering the emphatic nature of humankind, self-isolation or quarantine could have branched and serious repercussions upon humans’ psychological profile. The psycho-social impact is exponential, post-traumatic stress disorder (PTSD) and depression representing just two examples [ 26 ]. The gut–brain axis (GBA) component should not be neglected, since it is already known that a long-term loss of host eubiosis can promote psychiatric or neurodegenerative disorders [ 27 ].
Based on the above discussed, from our point of view, a two-sided approach is social confinement. López et al. [ 28 ] considered that social confinement should remain valid for at least 8 weeks because 99% of the current wave was attributed to humans intervention and recommended a resumption of daily activities up to 50%. Chakraborty et al. [ 29 ] sustained the arguments of López taking into consideration that people >65 years are more prone, and consider the necessity of an adequate medical center arrangement.
A study conducted by Williamson et al. [ 30 ] in which reunited a cohort consisting of over 17 million UK people demonstrated an increased risk among Black and South Asian people, predisposition attributed to age, sex, and related medical conditions. Miller et al. [ 31 ] assumed a case scenario in which around 20% of the US population will be infected, especially counties compared to the rest of the country. The authors created this pattern based on a series of assumptions such as transmission, contact patterns, basic reproductive rate, and how efficient quarantine really is.
Despite that travel restriction and social distancing significantly reduce the risk of transmissibility, evidence regarding the use of face masks are inconsistent. Regardless of the status of the individual, even for an asymptomatic carrier, face masks can mitigate the risk [ 32 ]. A recent systematic review and meta-analysis conducted by Chu et al., [ 33 ] reunited 172 observations studies across 16 countries with a cohort consisting of 25,697 patients. As expected, the greater the physical distance than 1 m, the risk is inversely proportional and vice versa. Intriguingly, even eye protection was positively associated with less infection.
However, a question arises. Why is there such a significant difference in the total number of deaths between countries? A cross-sectional dataset comprising 169 countries aiming to investigate factors associated with cross-country variation revealed that mortality rate is influenced by a series of variables; government effectiveness, the number of hospital beds, transport infrastructure, and the most important is the number of tests performed [ 34 ].
If all these amendments will not be taken seriously, we could face a second wave much more severe [ 35 ], reflected by the number of deaths reported each day. A similar event has been recorded as a consequence of the violation of these prevention measures in Romania.
An investigation of 12,343 SARS-CoV-2 genome sequences coming from the individual from 6 distinct geographical regions revealed that ORF1ab 4715L and S protein 614G variants is in direct correlation with fatality rates. The authors also showed that the bacillus Calmette–Guérin (BCG) vaccine and the frequency of several HLA alleles are associated with fatality rates and the number of infected cases [ 36 ].
From our point of view, researchers and clinicians should change the direction of this topic. Where does the next question come from? “If it is still known that angiotensin-converting enzyme 2 (ACE2) receptors [ 37 , 38 ] are also found in different niches along the digestive tract, why is the number of studies that aim to identify SARS-CoV-2 using rectal swabs or stool samples limited?” In several previous occasions, it has been demonstrated the presence of viral signatures in stool samples starting from day seven, and ranging up to almost two weeks after infection [ 39 , 40 , 41 , 42 ]. This hypothesis is also supported by additional evidence that the incidence of gastrointestinal deficiencies varies from mild [ 40 , 43 , 44 , 45 ] to moderate [ 46 , 47 , 48 , 49 ].
The temperature could play an important role in the spreading of this virus. Demongeot et al. [ 50 ] concluded that high temperatures restrict the range of action of SARS-CoV-2, but this does not mean that in the cold season there will not be big question marks as to whether or not a person is infected with SARS-CoV-2, especially when it will overlap with influenza infections.
In conclusion, Eastern European countries such as Romania are at particular risk because of the vulnerabilities in the health system, corruption, and emigration of doctors. All these delays and the poor organization represent the consequences of the communist regime that still makes its mark even after more than three decades. It should be noted that Romania has also faced several economic crises, the critical point being reached on February 5 this year, at which point it collapsed [ 51 ].
Identical to Western models, and consistent with WHO guidelines (distance between people of about 1.5 m, wearing a mask, isolation, and massive testing), all these measures have been implemented also in Romania. Despite the efforts made, the sums allocated for carrying out such tests are insignificant, the equipment is missing, the staff is not qualified, and the hospitals are at full capacity.
Cumulatively, all these negative aspects are certified by an increasing number of infected people in contrast to the rest of Europe where the situation has reached the upper limit and is now stabilizing. What is certain is that Romania does not yet have an effective strategy to reduce the number of patients.
Forecasting the prevalence of SARS-CoV-2 is imperative to date, especially for health departments. As has been described and demonstrated throughout this study, time-series models play a crucial role in disease prediction. In this study, ARIMA time-series models were applied with success with the aim of estimating the overall prevalence of COVID-19 in Romania. However, based on our expertise and although both software have proven effective, Statgraphics has a much wider spectrum of possibilities in terms of speed, analysis, and utility. To these arguments is added the current pandemic, where providing a clear perspective in a short interval is vital for every individual.
O.-D.I. (Conceptualization, Data curation, Investigation, Formal analysis, Methodology, Writing—original draft, Software); A.C. (Conceptualization, Methodology, Supervision, Validation, Project Administration, Writing—Review and Editing); B.D. (Conceptualization, Methodology, Supervision, Validation, Project Administration). All authors have read and agreed to the published version of the manuscript.
This research received no external funding.
The authors declare that they have no conflict of interest.
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Discover the world's research
Explore all metrics
This article presents a comprehensive review of the literature on the benefits, challenges, and limitations of using machine learning (ML) algorithms in inventory control, focusing on how these algorithms can transform inventory management and improve operational efficiency in supply chains. The originality of the study lies in its integrative approach, combining a detailed review with a critical analysis of current and future applications of ML in inventory control. The main aspects covered in the review include the types of ML algorithms most utilised in inventory control, key benefits such as replenishment optimisation and improved prediction accuracy, and the technical, ethical, and practical limitations in their implementation. The review also addresses challenges in managing high-dimensional data and adapting these algorithms to different operational contexts. The research method adopts a systematic approach to identify and analyse relevant sources, with a thorough bibliographic search resulting in a final corpus of 81 articles. The principal contribution of this research is a compendium of strategies for the implementation of ML in inventory control that leverages potential benefits while mitigating the technical and practical challenges that may arise, contributing to both theory and practice and providing valuable insights for academics and professionals in the industry, underscoring the potential and challenges of using ML in modern inventory control.
This is a preview of subscription content, log in via an institution to check access.
Subscribe and save.
Price includes VAT (Russian Federation)
Instant access to the full article PDF.
Rent this article via DeepDyve
Institutional subscriptions
Explore related subjects.
The sources used for doing this study is given in Sect. 2. Research method.
Albayrak Ünal, Ö., Erkayman, B., Usanmaz, B.: Applications of artificial intelligence in inventory management: a systematic review of the literature. Arch. Comput. Methods Eng. 30 (4), 2605–2625 (2023). https://doi.org/10.1007/s11831-022-09879-5
Article Google Scholar
Svoboda, J., Minner, S., Yao, M.: Typology and literature review on multiple supplier inventory control models. Eur. J. Oper. Res. 293 (1), 1–23 (2021). https://doi.org/10.1016/j.ejor.2020.11.023
Rolf, B., Jackson, I., Müller, M., Lang, S., Reggelin, T., Ivanov, D.: A review on reinforcement learning algorithms and applications in supply chain management. Int. J. Prod. Res. (2022). https://doi.org/10.1080/00207543.2022.2140221
Esteso, A., Peidro, D., Mula, J., Díaz-Madroñero, M.: Reinforcement learning applied to production planning and control. Int. J. Prod. Res. 61 (16), 5772–5789 (2023). https://doi.org/10.1080/00207543.2022.2104180
Jha, K., Doshi, A., Patel, P., Shah, M.: A comprehensive review on automation in agriculture using artificial intelligence. Artif. Intell. Agric. 2 , 1–12 (2019). https://doi.org/10.1016/j.aiia.2019.05.004
Tirkolaee, E.B., Sadeghi, S., Mooseloo, F.M., Vandchali, H.R., Aeini, S.: Application of machine learning in supply chain management: a comprehensive overview of the main areas. Math. Probl. Eng. 2021 , e1476043 (2021). https://doi.org/10.1155/2021/1476043
Boute, R.N., Gijsbrechts, J., van Jaarsveld, W., Vanvuchelen, N.: Deep reinforcement learning for inventory control: a roadmap. Eur. J. Oper. Res. 298 (2), 401–412 (2022). https://doi.org/10.1016/j.ejor.2021.07.016
Kamal, E., Abdel-Gawad, A.F., Zaki, S.: Neutrosophic-based machine learning techniques in the context of supply chain management: a survey. Int. J. Neutrosophic Sci. 21 (2), 142–160 (2023). https://doi.org/10.54216/IJNS.210213
Panda, S.K., Mohanty, S.N.: Time series forecasting and modeling of food demand supply chain based on regressors analysis. IEEE Access 11 , 42679–42700 (2023). https://doi.org/10.1109/ACCESS.2023.3266275
Ji, S., Wang, X., Zhao, W., Guo, D.: An application of a three-stage XGboost-based model to sales forecasting of a cross-border e-commerce enterprise. Math. Probl. Eng. (2019). https://doi.org/10.1155/2019/8503252
Shokouhifar, M., Ranjbarimesan, M.: Multivariate time-series blood donation/demand forecasting for resilient supply chain management during COVID-19 pandemic. Clean. Log. Supply Chain (2022). https://doi.org/10.1016/j.clscn.2022.100078
Wu, G., de Carvalho Servia, M.Á., Mowbray, M.: Distributional reinforcement learning for inventory management in multi-echelon supply chains. Dig. Chem. Eng. (2023). https://doi.org/10.1016/j.dche.2022.100073
Wu, J., Lu, C., Wu, C.: Learning-aided framework for storage control facing renewable energy. IEEE Syst. J. 17 (1), 652–663 (2023). https://doi.org/10.1109/JSYST.2022.3154389
Chong, J.W., Kim, W., Hong, J.S.: Optimisation of apparel supply chain using deep reinforcement learning. IEEE Access 10 , 100367–100375 (2022). https://doi.org/10.1109/ACCESS.2022.3205720
Maathavan, K.S.K., Venkatraman, S.: A secure encrypted classified electronic healthcare data for public cloud environment. Intell. Autom. Soft Comput. 32 (2), 765–779 (2022). https://doi.org/10.32604/iasc.2022.022276
Ntakolia, C., Kokkotis, C., Karlsson, P., Moustakidis, S.: An explainable machine learning model for material backorder prediction in inventory management. Sensors (2021). https://doi.org/10.3390/s21237926
Kegenbekov, Z., Jackson, I.: Adaptive supply chain: demand-supply synchronisation using deep reinforcement learning. Algorithms (2021). https://doi.org/10.3390/a14080240
Wang, K., Long, C., Ong, D.J., Zhang, J., Yuan, X.: Single-site perishable inventory management under uncertainties: a deep reinforcement learning approach. IEEE Trans. Knowl. Data Eng. (2023). https://doi.org/10.1109/TKDE.2023.3250249
Desloires, J., Ienco, D., Botrel, A.: Out-of-year corn yield prediction at field-scale using Sentinel-2 satellite imagery and machine learning methods. Comput. Electron. Agric. 209 , 107807 (2023). https://doi.org/10.1016/j.compag.2023.107807
Benhamida, F.Z., Kaddouri, O., Ouhrouche, T., Benaichouche, M., Casado-Mansilla, D., López-De-Ipiña, D.: Demand forecasting tool for inventory control smart systems. J. Commun. Softw. Syst. 17 (2), 185–196 (2021). https://doi.org/10.24138/jcomss-2021-0068
García-Barrios, D., Palomino, K., García-Solano, E., Cuello-Quiroz, A.: A machine learning based method for managing multiple impulse purchase products: an inventory management approach. J. Eng. Sci. Technol. Rev. 14 (1), 25–37 (2021). https://doi.org/10.25103/jestr.141.02
Qi, M., Mak, H.-Y., Shen, Z.-J.M.: Data-driven research in retail operations—a review. NRL 67 (8), 595–616 (2020). https://doi.org/10.1002/nav.21949
Do, H.-T., Pham, V.-C.: Deep learning based goods management in supermarkets. J. Adv. Inf. Technol. 12 (2), 164–168 (2021). https://doi.org/10.12720/jait.12.2.164-168
De Moor, B.J., Gijsbrechts, J., Boute, R.N.: Reward shaping to improve the performance of deep reinforcement learning in perishable inventory management. Eur. J. Oper. Res. 301 (2), 535–545 (2022). https://doi.org/10.1016/j.ejor.2021.10.045
Oroojlooyjadid, A., Snyder, L.V., Takáč, M.: Applying deep learning to the newsvendor problem. IISE Trans. 52 (4), 444–463 (2020). https://doi.org/10.1080/24725854.2019.1632502
Theodorou, E., Spiliotis, E., Assimakopoulos, V.: Optimising inventory control through a data-driven and model-independent framework. EURO J. Transp. Log. 12 , 100103 (2023). https://doi.org/10.1016/j.ejtl.2022.100103
Gružauskas, V., Gimžauskienė, E., Navickas, V.: Forecasting accuracy influence on logistics clusters activities: the case of the food industry. J. Clean. Prod. (2019). https://doi.org/10.1016/j.jclepro.2019.118225
Wang, S., Yang, Y.: M-GAN-XGBOOST model for sales prediction and precision marketing strategy making of each product in online stores. Data Technol. Appl. 55 (5), 749–770 (2021). https://doi.org/10.1108/DTA-11-2020-0286
Ren, X., Gong, Y., Rekik, Y., Xu, X.: Anticipatory shipping versus emergency shipment: data-driven optimal inventory models for online retailers. Int. J. Prod. Res. (2023). https://doi.org/10.1080/00207543.2023.2219343
Shih, H., Rajendran, S.: Comparison of time series methods and machine learning algorithms for forecasting Taiwan blood services foundation’s blood supply. J. Healthc. Eng. (2019). https://doi.org/10.1155/2019/6123745
Vicente, Ó.F., Fernández, F., García, J.: Automated market maker inventory management with deep reinforcement learning. Appl. Intell. (2023). https://doi.org/10.1007/s10489-023-04647-9
Demizu, T., Fukazawa, Y., Morita, H.: Inventory management of new products in retailers using model-based deep reinforcement learning. Expert Syst. Appl. 229 , 120256 (2023). https://doi.org/10.1016/j.eswa.2023.120256
Guo, M., Kong, X.T.R., Chan, H.K., Thadani, D.R.: Integrated inventory control and scheduling decision framework for packaging and products on a reusable transport item sharing platform. Int. J. Prod. Res. 61 (13), 4575–4591 (2023). https://doi.org/10.1080/00207543.2023.2187243
Hajek, P., Abedin, M.Z.: A profit function-maximizing inventory backorder prediction system using big data analytics. IEEE Access 8 , 58982–58994 (2020). https://doi.org/10.1109/ACCESS.2020.2983118
Behnamfar, R., Sajadi, S.M., Tootoonchy, M.: Developing environmental hedging point policy with variable demand: a machine learning approach. Int. J. Prod. Econ. 254 , 108640 (2022). https://doi.org/10.1016/j.ijpe.2022.108640
Zhang, P., Liu, X., Li, W., Yu, X.: Pharmaceutical cold chain management based on blockchain and deep learning. J. Int. Technol. 22 (7), 1531–1542 (2021). https://doi.org/10.53106/160792642021122207007
Priore, P., Ponte, B., Rosillo, R., de la Fuente, D.: Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments. Int. J. Prod. Res. 57 (11), 3663–3677 (2019). https://doi.org/10.1080/00207543.2018.1552369
Huerta-Soto, R., Ramirez-Asis, E., Tarazona-Jiménez, J., Nivin-Vargas, L., Norabuena-Figueroa, R., Guzman-Avalos, M., Reyes-Reyes, C.: Predictable inventory management within dairy supply chain operations. Int. J. Retail. Distrib. Manag. (2023). https://doi.org/10.1108/IJRDM-01-2023-0051
Galli, L., Levato, T., Schoen, F., Tigli, L.: Prescriptive analytics for inventory management in health care. J. Oper. Res. Soc. 72 (10), 2211–2224 (2021). https://doi.org/10.1080/01605682.2020.1776167
Wu, W.-S., Lu, Z.-M.: A real-time cup-detection method based on YOLOv3 for inventory management. Sensors (2022). https://doi.org/10.3390/s22186956
Dittrich, M.-A., Fohlmeister, S.: A deep q-learning-based optimisation of the inventory control in a linear process chain. Prod. Eng. 15 (1), 35–43 (2021). https://doi.org/10.1007/s11740-020-01000-8
Meisheri, H., Sultana, N.N., Baranwal, M., Baniwal, V., Nath, S., Verma, S., Ravindran, B., Khadilkar, H.: Scalable multi-product inventory control with lead time constraints using reinforcement learning. Neural Comput. Appl. 34 (3), 1735–1757 (2022). https://doi.org/10.1007/s00521-021-06129-w
Priya, R., Ramesh, D.: ML based sustainable precision agriculture: a future generation perspective. Sustain. Comput. Inf. Syst. (2020). https://doi.org/10.1016/j.suscom.2020.100439
Chandriah, K.K., Naraganahalli, R.V.: RNN/LSTM with modified Adam optimiser in deep learning approach for automobile spare parts demand forecasting. Multimedia Tools Appl. 80 (17), 26145–26159 (2021). https://doi.org/10.1007/s11042-021-10913-0
Koc, I., Arslan, E.: Dynamic ticket pricing of airlines using variant batch size interpretable multi-variable long short-term memory. Expert Syst. Appl. (2021). https://doi.org/10.1016/j.eswa.2021.114794
Fu, W., Chien, C.-F.: UNISON data-driven intermittent demand forecast framework to empower supply chain resilience and an empirical study in electronics distribution. Comput. Ind. Eng. 135 , 940–949 (2019). https://doi.org/10.1016/j.cie.2019.07.002
Hamandawana, P., Khan, A., Kim, J., Chung, T.-S.: Accelerating ML/DL applications with hierarchical caching on deduplication storage clusters. IEEE Trans. Big Data 8 (6), 1622–1636 (2022). https://doi.org/10.1109/TBDATA.2021.3106345
Huang, B., Gan, W., Li, Z.: Application of medical material inventory model under deep learning in supply planning of public emergency. IEEE Access 9 , 44128–44138 (2021). https://doi.org/10.1109/ACCESS.2021.3057869
Zhou, Q., Yang, Y., Fu, S.: Deep reinforcement learning approach for solving joint pricing and inventory problem with reference price effects. Expert Syst. Appl. (2022). https://doi.org/10.1016/j.eswa.2022.116564
Zhou, S., Sun, T., Xia, X., Zhang, N., Huang, B., Xian, G., Chai, X.: Library on-shelf book segmentation and recognition based on deep visual features. Inf. Process. Manag. 59 (6), 103101 (2022). https://doi.org/10.1016/j.ipm.2022.103101
de Paula Vidal, G.H., Caiado, R.G.G., Scavarda, L.F., Ivson, P., Garza-Reyes, J.A.: Decision support framework for inventory management combining fuzzy multicriteria methods, genetic algorithm, and artificial neural network. Comput. Ind. Eng. 174 , 108777 (2022). https://doi.org/10.1016/j.cie.2022.108777
Singh, R., Mishra, V.K.: Inventory model using Machine Learning for demand forecast with imperfect deteriorating products and partial backlogging under carbon emissions. Ann. Oper. Res. (2023). https://doi.org/10.1007/s10479-023-05518-9
Svoboda, J., Minner, S.: Tailoring inventory classification to industry applications: the benefits of understandable machine learning. Int. J. Prod. Res. 60 (1), 388–401 (2022). https://doi.org/10.1080/00207543.2021.1959078
Aguilar, J., Guillén, R.J.D.S., García, R., Gómez, C., Jerez, M., Narváez, M.L.J., Puerto, E.: A smart DDMRP model using machine learning techniques. Int. J. Value Chain Manag. 14 (2), 107–142 (2023). https://doi.org/10.1504/IJVCM.2023.130973
Badakhshan, E., Ball, P.: Applying digital twins for inventory and cash management in supply chains under physical and financial disruptions. Int. J. Prod. Res. 61 (15), 5094–5116 (2023). https://doi.org/10.1080/00207543.2022.2093682
Punia, S., Singh, S.P., Madaan, J.K.: From predictive to prescriptive analytics: a data-driven multi-item newsvendor model. Decision Support Syst (2020). https://doi.org/10.1016/j.dss.2020.113340
Kumar, N., Singh, B.J., Khope, P.: Unleashing an ML-based selection criteria for economic lot sizing in a smart batch-type production system. TQM J (2022). https://doi.org/10.1108/TQM-05-2022-0166
Ben Elmir, W., Hemmak, A., Senouci, B.: Smart platform for data blood bank management: forecasting demand in blood supply chain using machine learning. Information (Switzerland) (2023). https://doi.org/10.3390/info14010031
Tripathi, M.A., Madhavi, K., Kandi, V.S.P., Nassa, V.K., Mallik, B., Chakravarthi, M.K.: Machine learning models for evaluating the benefits of business intelligence systems. J. High Technol. Managem. Res. 34 (2), 100470 (2023). https://doi.org/10.1016/j.hitech.2023.100470
Van Belle, J., Guns, T., Verbeke, W.: Using shared sell-through data to forecast wholesaler demand in multi-echelon supply chains. Eur. J. Oper. Res. 288 (2), 466–479 (2021). https://doi.org/10.1016/j.ejor.2020.05.059
Clausen, J.B.B., Li, H.: Big data driven order-up-to level model: application of machine learning. Comput. Oper. Res. (2022). https://doi.org/10.1016/j.cor.2021.105641
Bertsimas, D., McCord, C., Sturt, B.: Dynamic optimisation with side information. Eur. J. Oper. Res. 304 (2), 634–651 (2023). https://doi.org/10.1016/j.ejor.2022.03.030
Kim, M., Lee, J., Lee, C., Jeong, J.: Framework of 2D KDE and LSTM-based forecasting for cost-effective inventory management in smart manufacturing. Appl Sci (Switzerland) (2022). https://doi.org/10.3390/app12052380
van Steenbergen, R.M., Mes, M.R.K.: Forecasting demand profiles of new products. Decis. Support. Syst. 139 , 113401 (2020). https://doi.org/10.1016/j.dss.2020.113401
Alzahrani, A., Asghar, M.Z.: Intelligent risk prediction system in iot-based supply chain management in logistics sector. Electronics (Switzerland) (2023). https://doi.org/10.3390/electronics12132760
Chen, Z.-Y., Fan, Z.-P., Sun, M.: Inventory management with multisource heterogeneous information: roles of representation learning and information fusion. IEEE Trans. Syst. Man Cybern. Syst. (2023). https://doi.org/10.1109/TSMC.2023.3267858
Juneja, A., Juneja, S., Soneja, A., Jain, S.: Real time object detection using CNN based single shot detector model. J. Inf. Technol. Manag. 13 (1), 62–80 (2021). https://doi.org/10.22059/jitm.2021.80025
Yang, K., Wang, Y., Fan, S., Mosleh, A.: Multi-criteria spare parts classification using the deep convolutional neural network method. Appl. Sci. (Switzerland) (2021). https://doi.org/10.3390/app11157088
Gijsbrechts, J., Boute, R.N., Van Mieghem, J.A., Zhang, D.J.: Can deep reinforcement learning improve inventory management? Performance on lost sales, dual-sourcing, and multi-echelon problems. Manuf. Serv. Oper. Manag. 24 (3), 1349–1368 (2022). https://doi.org/10.1287/msom.2021.1064
Wang, Q., Peng, Y., Yang, Y.: Solving inventory management problems through deep reinforcement learning. J. Syst. Sci. Syst. Eng. 31 (6), 677–689 (2022). https://doi.org/10.1007/s11518-022-5544-6
Zhou, Q., Fu, S., Yang, Y., Dong, C.: Joint pricing and inventory control with reference price effects and price thresholds: a deep reinforcement learning approach. Expert Syst. Appl. (2023). https://doi.org/10.1016/j.eswa.2023.120993
Bi, X., Adomavicius, G., Li, W., Qu, A.: Improving sales forecasting accuracy: a tensor factorization approach with demand awareness. INFORMS J. Comput. 34 (3), 1644–1660 (2022). https://doi.org/10.1287/ijoc.2021.1147
Kmiecik, M.: Logistics coordination based on inventory management and transportation planning by third-party logistics (3PL). Sustainability (Switzerland) (2022). https://doi.org/10.3390/su14138134
Ahmadi, E., Mosadegh, H., Maihami, R., Ghalehkhondabi, I., Sun, M., Süer, G.A.: Intelligent inventory management approaches for perishable pharmaceutical products in a healthcare supply chain. Comput. Oper. Res. (2022). https://doi.org/10.1016/j.cor.2022.105968
Wang, R., Gan, X., Li, Q., Yan, X.: Solving a joint pricing and inventory control problem for perishables via deep reinforcement learning. Complexity (2021). https://doi.org/10.1155/2021/6643131
Deng, C., Liu, Y.: A deep learning-based inventory management and demand prediction optimisation method for anomaly detection. Wirel. Commun. Mob. Comput. 2021 , e9969357 (2021). https://doi.org/10.1155/2021/9969357
Liu, L., Zhu, G., Zhao, X.: Application of medical supply inventory model based on deep learning and big data. Int. J. Syst. Assur. Eng. Manag. 13 , 1216–1227 (2022). https://doi.org/10.1007/s13198-022-01669-3
Zhang, S., Qin, X., Hu, S., Zhang, Q., Dong, B., Zhao, J.: Importance degree evaluation of spare parts based on clustering algorithm and back-propagation neural network. Math. Probl. Eng. (2020). https://doi.org/10.1155/2020/6161825
Lolli, F., Balugani, E., Ishizaka, A., Gamberini, R., Rimini, B., Regattieri, A.: Machine learning for multi-criteria inventory classification applied to intermittent demand. Prod. Plan. Control 30 (1), 76–89 (2019). https://doi.org/10.1080/09537287.2018.1525506
van Hezewijk, L., Dellaert, N., Van Woensel, T., Gademann, N.: Using the proximal policy optimisation algorithm for solving the stochastic capacitated lot sizing problem. Int. J. Prod. Res. 61 (6), 1955–1978 (2023). https://doi.org/10.1080/00207543.2022.2056540
Li, Z.: Consumer behavior analysis model based on machine learning. J. Intell. Fuzzy Syst. 40 (4), 6433–6443 (2021). https://doi.org/10.3233/JIFS-189483
Lu, S.: Enterprise supply chain risk assessment based on improved neural network algorithm and machine learning. J. Intell. Fuzzy Syst. 40 (4), 7013–7024 (2021). https://doi.org/10.3233/JIFS-189532
Li, N., Chiang, F., Down, D.G., Heddle, N.M.: A decision integration strategy for short-term demand forecasting and ordering for red blood cell components. Oper. Res. Health Care (2021). https://doi.org/10.1016/j.orhc.2021.100290
Merrad, Y., Habaebi, M.H., Islam, M.R., Gunawan, T.S.: A real-time mobile notification system for inventory stock out detection using SIFT and RANSAC. Int. J. Interact. Mobile Technol. 14 (5), 32–46 (2020). https://doi.org/10.3991/IJIM.V14I05.13315
Yang, B., Xu, X., Gong, Y., Rekik, Y.: Data-driven optimisation models for inventory and financing decisions in online retailing platforms. Ann. Oper. Res. (2023). https://doi.org/10.1007/s10479-023-05234-4
Qi, M., Shi, Y., Qi, Y., Ma, C., Yuan, R., Wu, D., Shen (Max), Z.-J.: A practical end-to-end inventory management model with deep learning. Manag. Sci. 69 (2), 759–773 (2023). https://doi.org/10.1287/mnsc.2022.4564
Iraola, E., Sedano, L., Nougués, J.M., Feliu, J.A., Coya, B., Batet, L.: SMART_TC: an R&D Programme on uses of artificial intelligence techniques for tritium monitoring in complex ITER-like tritium plant systems. Fusion Eng. Design (2021). https://doi.org/10.1016/j.fusengdes.2021.112409
Download references
Not applicable.
The authors declare that there is no funding agency involved in this project.
Authors and affiliations.
Universidad de Investigación y Desarrollo UDI, Bucaramanga, Colombia
Juan Camilo Gutierrez, Sonia Isabel Polo Triana & Juan Sebastian León Becerra
You can also search for this author in PubMed Google Scholar
All authors contributed equally to this paper, in content and in form.
Correspondence to Juan Camilo Gutierrez .
Conflict of interest.
The authors declare no conflict of interest.
The authors assure that the paper is the output of their own original work, which has not been previously published or sent anywhere to the best of their knowledge. All sources used are properly disclosed, and all authors have been personally and actively involved in substantial work leading to this paper.
All authors consent to the publication of this paper.
Publisher's note.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Reprints and permissions
Gutierrez, J.C., Polo Triana, S.I. & León Becerra, J.S. Benefits, challenges, and limitations of inventory control using machine learning algorithms: literature review. OPSEARCH (2024). https://doi.org/10.1007/s12597-024-00839-0
Download citation
Accepted : 05 August 2024
Published : 15 August 2024
DOI : https://doi.org/10.1007/s12597-024-00839-0
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .
Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.
Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.
Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.
Original Submission Date Received: .
Find support for a specific problem in the support section of our website.
Please let us know what you think of our products and services.
Visit our dedicated information section to learn more about MDPI.
Strengthening akis for sustainable agricultural features: insights and innovations from the european unio: a literature review.
2. materials and methods, 2.1. data collection procedure, 2.2. identification criteria, 2.3. screening and selection criteria, 2.4. eligibility and inclusion criteria.
4.1. akis and fas in the foreground through the new cap, 4.2. improving the effectiveness of an akis, 5. conclusions, author contributions, institutional review board statement, data availability statement, conflicts of interest.
Click here to enlarge figure
Article ID | Country | Factor(s) Investigated | Key Results Obtained | Suggested Improvements |
---|---|---|---|---|
[ ] Kiraly et al. (2023). | European Union countries | Assessing the behavior of European farmers, foresters and advisors regarding the frequency of searching for information on digital transformation using the EU Farmbook application. | ||
[ ] Ingram and Mills (2019). | European countries | Advisory services regarding sustainable soil management. | ||
[ ] Laurent et al. (2021). | Southwestern France | Evaluation of the processes by which farmers combine different sources of agricultural advice (micro-AKIS) for three types of innovation. | ||
[ ] Madureira et al. (2022). | Europe | The role of farm consultancy in agricultural innovation in relation to the microAKIS. | ||
[ ] Amerani et Michailidis (2023). | Greece | Evaluation of the contribution of the Greek AKIS and its adaptation to modern requirements of Greek agriculture | ||
[ ] Kiljunen et Jaakkola (2020). | Finland | AKIS and the Farm Advisory System in Finland. | ||
[ ] Charatsari et al. (2023). | Greece, Italy | Investigation of the possibility of AKIS actors to develop dynamic capacities during the supply process of the food chain. | ||
[ ] Masi et al. (2022). | Italy | Evaluation of precision agriculture tools as an innovation and the variables that facilitate or hinder their implementation in agricultural practice. | ||
[ ] Nordlund and Norrby (2021). | Sweden | Detailed description of the Swedish agricultural advisory services. | ||
[ ] Sturel (2021). | France | French AKIS and Farm Advisory System combined with the promotion of interactive innovation to support the transition in agriculture and forestry. | ||
[ ] Enfedaque Diaz et al. (2020). | Spain | AKIS and Advisory Services in Spain. | ||
[ ] Almeida et Viveiros (2020). | Portugal | Report of the AKIS in Portugal, with an emphasis on agricultural advisory services. | ||
[ ] Birke et al. (2021). | Germany | Overview of the AKIS and the Forestry Knowledge and Innovation System (FKIS) in Germany. | ||
[ ] Jelakovic (2021). | Croatia | Overview of the Croatian AKIS. | ||
[ ] Stankovic (2020). | Serbia | Report of the Serbian AKIS and FAS. | ||
[ ] Hrovatic (2020). | Slovenia | Description of the Slovenian AKIS and FAS. | ||
[ ] Bachev (2022). | Bulgaria | Analyzing Governance, Efficiency and Development of the AKIS. | ||
[ ] Koutsouris et al. (2020). | Cyprus | Comprehensive overview of the Cyprus AKIS and the Agricultural Advisory System. | ||
[ ] Knierim et al. (2019). | Germany | Smart Farming Technologies (SFT) and their degree of perception by farmers. | ||
[ ] Koutsouris et al. (2020) | Greece | AKIS and agricultural advisory services in Greece. | ||
[ ] Coquil et al. (2018). | France | The transformations of farmers and AKIS actors’ work during agroecological transitions. | ||
[ ] Lybaert et Debruyne (2020). | Belgium | Overview of the Belgian AKIS, focusing on agricultural advisory services. | ||
[ ] Dortmans et al. (2020). | Netherlands | Insight into the Dutch AKIS actors and factors that play a role in the system. | ||
[ ] Gaborne et al. (2020). | Hungary | The general characteristics of the Hungarian agricultural and forestry sector and AKIS, as well as the historical development of the advisory system. | ||
[ ] Oliveira et al. (2019). | Portugal | The Portuguese irrigation system of the Lis Valley, within the framework of the EIP AGRI Program of the European Union. | ||
[ ] Mirra et al. (2020). | Campania region, Italy | Analysis of the implementation of an experimental AKIS model through the RDP. | ||
[ ] Cristiano et al. (2020). | Italy | An overview of the Italian AKIS and the local Farm Advisory Services (FASs). | ||
[ ] Todorova (2021). | Bulgaria | A comprehensive description of the Bulgarian AKIS and FAS. | ||
[ ] Dzelme et Zurins (2021). | Latvia | A description of the AKIS in Latvia and brief outlook of the Forestry AKIS (FKIS). | ||
[ ] Matuseviciute et al. (2021). | Lithuania | AKIS and FAS in Lithuania. A detailed report. | ||
[ ] Zimmer et al. (2020). | Luxembourg | Description of the AKIS in Luxembourg. | ||
[ ] Giagnocavo et al. (2022). | Spain | The reconnection of the farm production system with nature, especially where the production procedure is embedded in less sustainable conventional or dominant regimes and landscapes. | ||
[ ] Klitgaard (2019). | Denmark | A comprehensive description of the AKIS and FAS in Denmark. | ||
[ ] Cristiano et al. (2020). | Malta | Description of the AKIS with a focus in the FAS in the Republic of Malta. | ||
[ ] Knierim et al. (2015) | Belgium, France, Ireland, Germany, Portugal and the UK | The AKIS concept in selected EU member states. | ||
[ ] Terziev and Arabska (2015). | Bulgaria | Quality assurance and sustainable development in the agri-food sector. | ||
[ ] Konecna (2020). | Czech Republic | A comprehensive description of theAKIS in the Czech Republic, with a particular focus on farm and forestry advisory services. | ||
[ ] Kasdorferova et al. (2020). | Slovak Republic | Description of the AKIS and FAS in Slovak Republic. | ||
[ ] Boczek et al. (2020). | Poland | An overview of the AKIS and FKIS, as well as the FAS in Poland. | ||
[ ] Ingram et al. (2022). | Europe countries | Evaluation of the advisory services of European countries in the context of sustainable soil management. | ||
[ ] Herzog et Neubauer (2020). | Austria | Evaluation of the Austrian AKIS. | ||
[ ] Banninger (2021). | Switzerland | Description of the Swiss AKIS and advisory services. | ||
[ ] Maher (2020). | Republic of Ireland | Description of the Irish AKIS, with an emphasis on methods of knowledge dissemination and innovation. | ||
[ ] Dunne et al. (2019). | Laois county, Republic of Ireland | Evaluating the interaction characteristics of public and private Farm Advisory Services in County Laois, Ireland. | ||
[ ] Knuth and Knierim (2014). | Germany | Scientific bodies and providers of agricultural advisory services: finding ways to strengthen their relationship. | ||
[ ] Konecna (2018). | Czach Republic | Evaluation of the Institute of Agricultural Economy and Information (IAEI) regarding its innovation potential. | ||
[ ] Hermans et al. (2019). | England, France, Germany, Hungary, Italy, Latvia, the Netherlands, Switzerland | Effect of AKIS structural factors of eight European countries on cooperative schemes or social learning in innovation networks. | ||
[ ] Klerkx et al. (2017). | Norway | Challenges for advisory services in serving various types of farmers seeking and acquiring farm business advice. | ||
[ ] Tamsalu (2021). | Estonia | Presentation of the AKIS in Estonia. | ||
[ ] Kania and Zmija (2016). | Poland | How cooperation between AKIS stakeholders is assessed from the standpoint of the 16 provincial Agricultural Advisory Centers (ODRs). |
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Kountios, G.; Kanakaris, S.; Moulogianni, C.; Bournaris, T. Strengthening AKIS for Sustainable Agricultural Features: Insights and Innovations from the European Unio: A Literature Review. Sustainability 2024 , 16 , 7068. https://doi.org/10.3390/su16167068
Kountios G, Kanakaris S, Moulogianni C, Bournaris T. Strengthening AKIS for Sustainable Agricultural Features: Insights and Innovations from the European Unio: A Literature Review. Sustainability . 2024; 16(16):7068. https://doi.org/10.3390/su16167068
Kountios, Georgios, Spyridon Kanakaris, Christina Moulogianni, and Thomas Bournaris. 2024. "Strengthening AKIS for Sustainable Agricultural Features: Insights and Innovations from the European Unio: A Literature Review" Sustainability 16, no. 16: 7068. https://doi.org/10.3390/su16167068
Article access statistics, further information, mdpi initiatives, follow mdpi.
Subscribe to receive issue release notifications and newsletters from MDPI journals
IMAGES
COMMENTS
ARIMA model. Jamal Fattah. 1, Latifa Ezzine. 1, Zineb Aman. 2, Haj El Moussami. 2 ... section presents a literature review about demand forecast-ing studies. The third section is consecrated to ...
This brief review of the literature shows that ANN is a strength tool aiming at the modeling of any time series. Nevertheless, in our article, we will test the ARIMA model at first to prove its ability to make accurate forecasts in the food company as a priori study. ... It is clear from Table 2 that the ARIMA model (1, 0, 1) is selected ...
In that scope, the first model category to be presented in detail is ARIMA, which is the center of our review, and then we organize the machine learning approaches by model category. For each of the categories, we present the theoretical background, and then we demonstrate the relevant scientific literature organized by application category.
The ARIMA model is a generalization of the ARMA model (AutoRegressive Moving A verage model), suitable for handling non-stationary time series. As the classical ARMA
This article discusses the use of autoregressive integrated moving average (ARIMA) models for time series analysis. Rather than forecasting future values, we focus here on examining change across time in outcomes of interest and how this change is related to relevant variables. Much of the data that we collect about the world around us—stock prices, unemployment rates, party identification ...
• Inotherwords,thereissomenon-uniqueness ofredundancy intheparametrization—differentchoices ofparameterswillactuallyleadtothesamebehaviorinthemodelattheend
The ARIMA model relies on the number of positive cases, the number of performed tests per day and the average positive percentage. In the United Kingdom, weighted interval scoring was used for the prediction model, which used the data from the linear progression of 7-day cases[ 42 ].
important time series forecasting models have been evolved in literature. One of the most popular and frequently used stochastic time series models is the Autoregressive Integrated Moving Average (ARIMA) [6, 8, 21, 23] model. The basic assumption made to implement this model is that the considered time series is linear and
model. The two methods are used to forecast the failure of the system.8 Aburto and Weber9 combined the two forecasting meth-ods which are ARIMA and neural networks. The efficiency of the hybrid model is compared with traditional forecast-ing methods.10 This brief review of the literature shows that ANN is a
ARIMA approaches. The well-known traditional statistics time series forecasting methods, such as ARIMA and its variants 17,21 -29 are still used a lot because of their efficiency level. Table 1 presents a summary of ARIMA-based approaches for SPF. For the articles reviewed, we summarize the methods used, comparison methods, datasets, target outputs, input features, metrics evaluations, and ...
ARIMA models are mathematically written as ARIMA(p,d,q), where p and q are same as ARMA model but d = number of first differences (Yu, G. and Zhang, C., 2004, May). I. Seasonal Autoregressive ...
Although the ARIMA model is a powerful model for analyzing patterns in univariate time-series data, it commits errors when handling seasonal data. Adding seasonal order to the model enhances its performance. SARIMA extends the ARIMA model. It considers the seasonal component when modeling time-series data.
ARIMA, SARIMA, and the Additive Model Time-series analysis is a method for explaining sequential problems. It is convenient when a continuous variable is time-dependent. In finance, we frequently use it to discover consistent patterns in the market data and forecast future prices. This chapter offers a comprehensive introduction
suggested that ARIMA models might well make suitable forecasting models since it turned out that many of the previous ad hoc methods were represented as special cases: for example the ARIMA(0,1,1) model leads to forecasts produced by an EWMA, while the ARIMA(0,2,2) corresponds to Holts method (1957).7
Literature review. Full size table. The core analysis of this paper is the outtake of well-known forecasting frameworks such as Exponential smoothing, ARIMA, LSTM, and ANN. A hybridization of ARIMA and ANN methods consisting of linear and nonlinear components is implemented. ... Using the ARIMA model for forecasting, it is presumed that the ...
The performance of the chosen ARIMA model is confirmed when comparing its forecasts with real data reported after the forecast period. The study successfully forecasts both confirmed and recovered COVID-19 cases across the preventive plan phases in Recife. ... The introduction in Section 1 includes a literature review of existing research on ...
Hence, the superiority of forecasting ability of the ARIMA model over the other machine learning methods and AI models has been established by expanding amount of literature on ARIMA modelling (Ceylan, 2020; Fong et al., 2020; Kyungjoo et al., 2007; Merh et al., 2010; Singh et al., 2020).The ARIMA modelling has been successfully applied in the past literature to predict the prevalence of ...
literature given mostly all previous studies focus on yearly data. Following the introduction, review of literature2 is presented. In next section I give an overview of the data sources used. In next section thereafter, ARIMA model and assumptions are detailed and then detailed modelling, analysis and results are presented.
Abstract This paper reviews the approach to forecasting based on the construction of ARIMA time series models. Recent developments in this area are surveyed, and the approach is related to other fo...
Driven strongly by a review of the literature, we selected traditional time series models ARIMA and GARCH and the deep learning model (LSTM) for the present investigation. First, the ARIMA model has been applied to check the mean behaviour of the series. ... B2, B3). ARIMA model squared residuals were used to estimate input lag through ACF and ...
Abstract. Time series classification is a supervised learning problem that aims at labelling time series according to their class belongingness. Time series can be of variable length. Many algorithms have been proposed, among which feature-based approaches play a key role, but not all of them are able to deal with time series of unequal lengths.
Building an ARIMA model for any given time-series involves the checking of four steps: assessment of the model, estimation of parameters, diagnostic checking, and prediction. The first, which is otherwise imperative, is to verify if the mean, variance, and autocorrelation of the time-series are consistent throughout the established interval [ 20 ].
Many authors have conducted a comparison between the traditional methods, such as the ARIMA model, and ML methods, such as SVR and LSTM models, in forecasting financial time series (Sheta et al ...
The construction industry plays a pivotal role in China's achievement of its "dual carbon" goals. This study conducts a decomposition analysis of the carbon emissions from the construction industry (CECI) at both national and provincial levels for the period 2010-2020 and employs the ARIMA model to predict the short-term peak trends at the provincial level. The findings are as follows ...
A narrative literature review was conducted, synthesizing data from 96 peer-reviewed journal articles, books, and authoritative reports from databases such as PubMed, PsycINFO, and Google Scholar. The review focused on studies related to trauma, post-traumatic stress disorder (PTSD), complex trauma, and related disorders, emphasizing both ...
This article presents a comprehensive review of the literature on the benefits, challenges, and limitations of using machine learning (ML) algorithms in inventory control, focusing on how these algorithms can transform inventory management and improve operational efficiency in supply chains. ... The configured ARIMA model is then used to ...
The Agricultural Knowledge and Innovation System (AKIS) and the Farm Advisory Service (FAS) are important elements of the current Programming Period of the Common Agricultural Policy (2023-2027), as it is now deemed necessary to transition the European agricultural model to more sustainable forms, through the dissemination of agricultural knowledge, while simultaneously promoting innovative ...