Evaluation and Potential Analysis of Saving Opportunities in Agricultural Enterprises

Öz

The primary objective of this study is to assess potential savings opportunities in agricultural enterprises and to determine their feasibility. To this end, face-to-face interviews were conducted with 268 agricultural enterprises in Turkey, selected according to the stratified random sampling method. The results of the interviews revealed the amount of savings accrued by agricultural enterprises and the factors influencing the formation of savings. The data obtained was then used to determine the savings potential of agricultural enterprises using artificial neural networks. The classification analysis in the artificial neural network model enables the prediction of the savings potential of enterprises by classifying them according to all the variables included in the model, in comparison to the classification made with the existing data. This approach allows for the consideration of not only financial indicators but also socio-economic factors, personal factors and environmental factors in determining savings policies, thereby revealing the actual potential of the enterprises. To determine the savings potential of the analyzed enterprises, 29 different models in 9 model classes were tested. Consequently, the model class with the highest accuracy was identified as decision trees. The accuracy of decision trees varies between 82.5% and 85.1%. While 62.69% of the enterprises exhibited high savings because of the modelling process, this value was determined as 60.8% because of the prediction model. Furthermore, the proportion of enterprises with low savings, which was estimated at 32.84% in the data model, was found to be 35.8% in the prediction model. Additionally, the proportion of enterprises with negative savings was determined to be 4.48% in the data model and 3.4% in the prediction model. The study identified the structural, social and economic characteristics of enterprises according to their savings structures and evaluated potential for increasing savings. It was determined that agricultural enterprises should focus on ways to increase savings, increase income, keep expenses under control and make investments for the future. Efficient farming techniques, the formation of agricultural cooperatives and marketing associations, the reduction of energy and input costs, the effective utilization of agricultural machinery, and the investment in renewable energy sources could assist agribusinesses in increasing their economic security and sustainability. All these steps enable agricultural households to have a stronger and more sustainable financial structure and contribute to the economic development of rural areas.

Anahtar Kelimeler

• Savings
• Agricultural enterprises
• Artificial neural networks

Tarım İşletmelerinde Tasarruf Fırsatlarının Değerlendirilmesi ve Potansiyel Analizi

Öz

Bu çalışmanın temel amacı tarım işletmelerinde tasarruf fırsatlarının değerlendirilmesi ve potansiyellerinin belirlenmesidir. Bu amaca yönelik olarak Türkiye’deki tabakalı tesadüfi örnekleme yöntemine göre belirlenen 268 tarım işletmesiyle yüz yüze anket yöntemiyle mülakatlar yapılmıştır. Mülakatlar sonucunda tarım işletmelerinin tasarruf miktarları ve tasarrufların oluşumları üzerindeki etkili olan faktörler belirlenmiştir. Elde edilen veriler sonucunda tarım işletmelerinin tasarruf potansiyellerini belirlemek için yapay sinir ağları kullanılmıştır. Yapay sinir ağları modelinde sınıflandırma analizi mevcut verilerle yapılan sınıflandırmaya karşı modele dahil edilen tüm değişkenlerle birlikte işletmeleri sınıflandırarak işletmelerin tasarruf potansiyellerine yönelik tahminlerde bulunmaktadır. Böylece tasarruf politikalarının belirlenmesinde sadece finansal göstergeler değil aynı zamanda sosyo-ekonomik faktörler, kişisel faktörler ve çevresel faktörler de göz önünde bulundurularak gerçek potansiyeller ortaya çıkarılmıştır. İncelenen işletmelerde tasarruf yapma potansiyellerini belirlemek amacıyla 9 model sınıfında farklı 29 model test edilmiştir. Buna göre en yüksek doğruluk payına sahip model sınıfı karar ağaçları olarak belirlenmiştir. Karar ağaçlarının doğruluk payları %82,5-%85,1 arasında değişmektedir. Yapılan modelleme sonucunda işletmelerin %62,69’u yüksek tasarrufa sahip iken tahmin modeli sonucunda bu değer %60,8 olarak belirlenmiştir. Ayrıca veri modelinde %32,84 olarak belirlenen düşük tasarruflu işletmelerin oranı tahmin modelinde %35,8 olarak tespit edilmiş olup negatif işletmelerin oranı veri modelinde %4,48 ve tahmin modelinde %3,4 olarak bulunmuştur. Çalışmanın sonucunda tasarruf yapılarına göre işletmelerin yapısal, sosyal ve ekonomik özellikleri küme halinde gösterilerek tasarruf potansiyellerinin artırılmasına yönelik değerlendirmeler yapılmıştır. Çalışma sonucunda tarım işletmelerinin tasarrufu artırma yolları, gelir artırma, giderleri kontrol altında tutma ve geleceğe yönelik yatırımlar yapma üzerine odaklanması gerekliliği belirlenmiştir. Verimli tarım teknikleri kullanmak, tarım kooperatifleri ve pazarlama birliklerine katılmak, enerji ve girdi maliyetlerini azaltmak, tarım makinelerini etkili bir şekilde kullanmak ve yenilenebilir enerji kaynaklarına yatırım yapmak gibi stratejiler, tarım işletmelerinin ekonomik güvenliği ve sürdürülebilirliklerini artırmalarına yardımcı olabilir. Tüm bu adımlar, tarım hane halklarının daha güçlü ve sürdürülebilir bir finansal yapıya sahip olmalarını sağlar ve kırsal kesimin ekonomik kalkınmasına katkıda bulunabilir.

Anahtar Kelimeler

• Tasarruf
• Tarım İşletmeleri
• Yapay Sinir Ağları

Kaynakça

1. Abegunde, V. O., Sibanda, M. and Obi, A. (2019). Determinants of the adoption of climate-smart agricultural practices by small-scale farming households in King Cetshwayo District Municipality, South Africa. Sustainability, 12(1): 195.
2. Akal, D. and Umut, I. (2022). Using artificial ıntelligence methods for power estimation in photovoltaic panels. Journal of Tekirdağ Faculty of Agriculture, 19(2): 435-445.
3. Aktürk, D., Bayramoğlu, Z. and Savran, F. (2012). Application of Classification and Regression Tree Method with Sample Data Set. 10th National Agricultural Economics Congress. 5-7 September, P. 817-823, Konya, Türkiye.
4. Alan, M. A. (2014). Classification of student data with decision trees. Ataturk University Journal of Economics & Administrative Sciences, 28(4): 101-112.
5. Altaş, D. and Gülpınar, V. (2012). Comparison of classification performance of decision trees and artificial neural networks. Trakya University Journal of Social Sciences, 14(1): 1-22.
6. Aryal, J. P., Rahut, D. B., Maharjan, S. and Erenstein, O. (2018). Factors affecting the adoption of multiple climate‐smart agricultural practices in the Indo‐Gangetic Plains of India. Natural Resources Forum, 42(3): 141-158.
7. Baitu, G. P., Gadalla, O. A. A. and Öztekin, Y. B. (2023). Traditional machine learning-based classification of cashew kernels using colour features. Journal of Tekirdag Agricultural Faculty, 20(1): 115-124.
8. Bayramoğlu, Z., Çelik, Y., Doğan, H. G., Karakayacı, Z. and Ağızan, K. (2023). Investigation of sectoral distribution of savings and expenditures in agricultural enterprises. TÜBİTAK (121K160) Project Final Report.

9. Bounsaythip, C. and Rinta-Runsala, E. (2001). Overview of data mining for customer behavior modeling. VTT Information Technology Research Report, Version, 1: 1-53.
10. Edwards-Murphy, F., Magno, M., Whelan, P. M., O’Halloran, J. and Popovici, E. M. (2016). b+ WSN: Smart beehive with preliminary decision tree analysis for agriculture and honey bee health monitoring. Computers and Electronics in Agriculture, 124: 211-219.
11. Emel, G. G. and Taşkın, Ç. (2005). Decision trees in data mining and a sales analysis application. Eskisehir Osmangazi University Journal of Social Sciences, 6(2): 221-239 (In Turkısh).
12. Erdem, B. P. (2017). Factors Affecting Household Savings in Turkey (Vol. 2973). General Directorate of Economic Models and Strategic Research, Ankara, Türkiye (In Turkısh).
13. Gikonyo, N. W., Busienei, J. R., Gathiaka, J. K. and Karuku, G. N. (2022). Analysis of household savings and adoption of climate smart agricultural technologies evidence from smallholder farmers in Nyando Basin, Kenya. Heliyon, 8(6): 1-9.
14. Hamaker, C. M. and Patrick, G. F. (1996). Farmers and alternative retirement investment strategies. Journal of ASFMRA, 4(2): 42-51.
15. Jensen, F. E. and Pope, R. D. (2004). Agricultural precautionary wealth. Journal of Agricultural and Resource Economics, 29(1): 17-30.
16. Kadirhanoğulları, İ. H., Karadaş, K., Özger, Ö. and Konu, M. (2021). Determination of organic product consumer preferences with decision tree algorithms: Iğdır province case. Yuzuncu Yil University Journal of Agricultural Sciences, 31(1): 188-196 (In Turkish).
17. Karaaslan, K. Ç., Oktay, E. and Alkan, Ö. (2022). Determinants of household saving behaviour in Turkey. Sosyoekonomi, 30(51): 71-90.
18. Karagöl, E.T. and Özkan, B. (2014). Savings for Sustainable Growth. Foundation for Political, Economic and Social Research (SETA) Publishers, Ankara, Türkiye.
19. Karahan, M. (2011). Statistical forecasting methods: Product demand forecasting with artificial neural networks. (Ph.D. Thesis) Selcuk University, Institute of Social Sciences, Konya, Türkiye.
20. Kavzoğlu, T. and Çölkesen, İ. (2010). Classification of satellite images with decision trees. Electronic Journal of Map Technologies, 2(1): 36-45.
21. Kayabasi, A., Toktas, A., Sabanci, K. and Yigit, E. (2018). Automatic classification of agricultural grains: Comparison of neural networks. Neural Network World, 28(3): 213-224.
22. Kozera, A., Glowicka-Woloszyn, R. and Stanislawska, R. (2016). Savings behaviour in households of farmers as compared to other socio-economic groups in Poland. Journal of Agribusiness and Rural Development, 4(42): 557-566.
23. Kujawa, S. and Niedbała, G. (2021). Artificial neural networks in agriculture. Agriculture, 11(6): 497-563.
24. Kurgat, B. K., Lamanna, C., Kimaro, A., Namoi, N., Manda, L. and Rosenstock, T. S. (2020). Adoption of climate-smart agriculture technologies in Tanzania. Frontiers in Sustainable Food Systems, 4(55): 1-9.
25. Léon, Y. and Rainelli, P. (1976). Savings of farmers: A cross-section analysis. European Review of Agricultural Economics, 3(4): 501-522.
26. Lidi, B. Y., Amsalu, B. and Belina, M. (2017). Determinants of saving behavior of farm households in rural Ethiopia: The double hurdle approach. Journal of Economics and Sustainable Development, 8(19): 33-42.
27. Loiko, V., Loiko, D. and Lekh, D. (2019). Ensuring of the financial security of agricultural enterprise enterprises. Agrosvit, 24: 28-34.
28. Maheshwari, T. (2016). Saving and ınvestment behaviour of rural household (with special reference to coimbatore district). International Journal of Multidisciplinary Research and Development, 3(3): 2349-4182.
29. Mapesa, H. J. (2015). Shaping the saving behaviour of the rural poor: Experiences of rural finance programmes in Tanzania. International Journal of Research in Business Management, 3(2): 47-56.
30. Naranchimeg, L., Khurelbaatar, B. and Baasandor, L. (2023). Asset financing analysis of business enterprises. iBusiness, 15(1): 26-37.
31. Nayak, S. (2013). Determinants and pattern of saving behavior in the rural households of western odisha. (MSc. Thesis). National Institute of Technology, Department of Humanities and Social Sciences, Tiruchirappalli, India.
32. Njegomir, V., Tepavac, R. and Ivanišević, N. (2017). Alternative sources of financing entrepreneurial undertakings in agriculture. Економика пољопривреде, 64(1): 295-306.
33. Pagliacci, F., Defrancesco, E., Mozzato, D., Bortolini, L., Pezzuolo, A., Pirotti, F., Pisani, E. and Gatto, P. (2020). Drivers of farmers' adoption and continuation of climate-smart agricultural practices a study from northeastern Italy. Science of The Total Environment, 710 (2020): 1-13.
34. Sabancı, K., Aydın, C. and Ünlerşen, M.F. (2012). Determination of potato classification parameters using image processing and artificial neural networks. Journal of the Institute of Science and Technology, 2(2): 59-62 (In Turkish).
35. Sancak, E. and Demirci, N. (2012). National savings and the importance of savings for sustainable growth in Turkey. The International Journal of Economic and Social Research, 8(2): 159-198 (In Turkish).
36. Sãžrbulescu, E. C., Luminiå, P. and Tiberiu, I. (2015). The financial resources of agriculture. Lucrări Științifice Management Agricol, 17(3): 12.
37. Sönmez, S. and Artukoğlu, M. (2021). A research on factors affecting saving tendency in rural areas. Journal of Adnan Menderes University Faculty of Agriculture, 18(2): 189-195 (In Turkish).
38. Sönmez, S. and Artukoğlu, M. (2022). A research on determining the ıncome status and savings of rural people: The case of Izmir Province. Journal of Agricultural Economics, 28(2): 173-182 (In Turkish).
39. Spence, L. C. and Mapp, H. P. (1976). A retirement income simulation model for farm operators. Journal of Agricultural and Applied Economics, 8(1): 163-168.
40. Strzelecka, A. and Zawadzka, D. (2023). Savings as a source of financial energy on the farm—what determines the accumulation of savings by agricultural households? Model approach. Energies, 16(2): 1-18.
41. Suresh, M., Sangeetha, D. and Kumaraswamy, S. (2019). Modelling of Factors Influencing Saving Behaviour of Women in India: An Interpretive Structural Modelling. International Conference on Advances in Materials Research. P. 809-818, Singapore.
42. Taner, A., Tekgüler, A. and Hüseyin, S. (2015). Classification of durum wheat varieties by artificial neural networks. Anatolian Journal of Agricultural Sciences, 30(1): 51-59 (In Turkish).
43. Teshome, G., Kassa, B., Emana, B. and Haji, J. (2013). Determinants of rural household savings in Ethiopia: The case of east Hararghe Zone, Oromia regional state. Journal of Economics and Sustainable Development, 4(3): 66-75.
44. Uddin, M. N., Bokelmann, W. and Entsminger, J. S. (2014). Factors affecting farmers’ adaptation strategies to environmental degradation and climate change effects: A farm level study in Bangladesh. Climate, 2(4): 223-241.
45. Waheed, T., Bonnell, R., Prasher, S. O. and Paulet, E. (2006). Measuring performance in precision agriculture: CART—A decision tree approach. Agricultural Water Management, 84(1-2): 173-185.
46. Wang, H., Zhang, M. and Cai, Y. (2009). Problems, challenges, and strategic options of grain security in China. Advances in Agronomy, 103: 101-147.
47. Wu, J., Olesnikova, A., Song, C.-H. and Lee, W. D. (2009). The development and application of decision tree for agriculture data. 2009 Second International Symposium on Intelligent Information Technology and Security Informatics. January 23-25, P. 16-20, Moscow, Russia.
48. Yamane, T. (1967). Statistics. Harper & Row; Publishers, New York, U.S.A.
49. Yüksek, A. G. (2007). Comparison of multiple regression analysis and artificial neural network method in air pollution forecasting. (Ph.D. Thesis). Sivas Cumhuriyet University, Social Sciences Institute, Sivas, Türkiye (In Turkish).
50. Zeng, M., Du, J., Zhu, X. and Deng, X. (2023). Does internet use drive rural household savings? Evidence from 7825 farmer households in rural China. Finance Research Letters, 57(104275): 1-13.
51. Zengin, S., Yüksel, S. and Kartal, M. T. (2018). A study to determine the factors causing low household savings in Turkey. Journal of Yasar University, 13(49): 86-100.
52. Гринюк, Н., Докієнко, Л., Левченко, В. and Тринчук, В. (2023). Capital structure as a criterion of efficient management of the corporation's financial recourses. Financial and Credit Activity Problems of Theory and Practice, 2(49): 326-337.