Modelling Livelihood Security among Tribal Farmers in South Odisha using Machine Learning

Swapnamay Ghosh; Ashok Kumar; Ajay Kumar Prusty; Akkamahadevi Naik; Chitrasena Padhy

doi:10.48165/IJEE.2025.61423

Authors

Swapnamay Ghosh M.Sc. Scholar, Department of Agricultural Extension Education, MSSSoA, Centurion University of Technology & Management, Paralakhemundi, Odisha
Ashok Kumar Associate Professor, Department of Agricultural Extension Education, MSSSoA, Centurion University of Technology & Management, Paralakhemundi, Odisha
Ajay Kumar Prusty Associate Professor, Department of Agricultural Extension Education, MSSSoA, Centurion University of Technology & Management, Paralakhemundi, Odisha https://orcid.org/0000-0003-3670-802X
Akkamahadevi Naik Assistant Professor, Department of Agricultural Extension Education, MSSSoA, Centurion University of Technology & Management, Paralakhemundi, Odisha
Chitrasena Padhy Associate Professor, Department of Agricultural Extension Education, MSSSoA, Centurion University of Technology & Management, Paralakhemundi, Odisha

https://doi.org/10.48165/IJEE.2025.61423

Keywords:

livelihood security, tribal farmers, South Odisha, Random Forest, SHAP

Abstract

Tribal farming systems ensure livelihood security through complex socio-economic and behavioural interactions that defy simple linear models. The study analysed primary data collected through simple random sampling method from 180 households in Gajapati and Rayagada districts of Odisha during 2023-24 to analysethe Livelihood Security score using a Random Forest regression. Out-of-bag validation demonstrated model stability with an R² of approximately 0.865 using around 400 trees. The age was the most significant predictor, followed by self-confidence, with smaller contributions from management orientation and innovative proneness. One- and two-dimensional partial dependence outcomes highlighted non-linear age effects and interactions, indicating that increased confidence and enhanced management capacity improve predicted livelihood security across all age groups. These results suggest actionable strategies for agricultural extension: implementing confidence-building and management training tailored to life-stage constraints could yield substantial benefits. Limitations include the correlational nature of the data and the reliance on partial dependence.

References

Amghani, M. S., Sabouri, M. S., Baghernejad, J., &Norozi, A. (2025). Factors affecting the livelihood sustainability of smallholder farmers in Iran. Environmental and Sustainability Indicators, 26, 100601.https://doi.org/10.1016/j.indic.2025.100601

Apley, D. W., & Zhu, J. (2020). Visualizing the effects of predictor variables in black box supervised learning models. Journal of the Royal Statistical Society Series B: Statistical Methodology, 82(4), 1059-1086.https://doi.org/10.1111/rssb.12377

Baul, T., Karlan, D., Toyama, K., &Vasilaky, K. (2024). Improving smallholder agriculture via video-based group extension. Journal of Development Economics, 169, 103267.https://doi.org/10.1016/j.jdeveco.2024.103267

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.https://doi.org/10.1023/A:1010933404324

Das, N., Modak, S., Prusty, A. K., Saha, P., & Suman, S. (2025). Understanding and overcoming key challenges of agripreneurs in Southern Odisha: A case study. Indian Journal of Extension Education, 61(2), 118–122. https://doi.org/10.48165/IJEE.2025.612RN05

Goldstein, A., Kapelner, A., Bleich, J., & Pitkin, E. (2015). Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. journal of Computational and Graphical Statistics, 24(1), 44-65.https://doi.org/10.1080/10618600.2014.907095

Kerketa, A., Ray, P., Padhy, C., Patra, S. K., Raj, R. K., Mishra, N., & Prasanna, V. (2025). Analysis of adoption practices of SRI in tribal region of Sundargarh district in Odisha. Indian Journal of Extension Education, 61(2), 101–104. https://doi.org/10.48165/IJEE.2025.612RN01

Kumari, A., Deb, A., Prusty, A. K., Suman, S., Rout, D. S., & Amar, A. K. (2024). Preservation of the Indigenous Medicinal Knowledge Network of the Bonda Tribe. Indian Journal of Extension Education, 60(4), 40–46. https://doi.org/10.48165/IJEE.2024.60408

Lekang B., Nain M.S., Singh R., Sharma J.P., & Singh D.R. (2017) Factors influencing the utility of experiential learning programme of Indian Council of Agricultural Research. Indian Journal of Agricultural Sciences,87(3),325-36

Lekang B., Nain M. S., Singh R. & Sharma J.P. (2016). Perceived utility of experiential learning programme of Indian Council of Agricultural Research. Indian Journal of Agricultural Sciences, 86(12), 1536-1546.

Levene, H. (1960). Robust tests for equality of variances. Contributions to Probability and Statistics, 278-292.

Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.

Magakwe, A., Olorunfemi, O., & Sithole, A. (2025). Factors influencing smallholder farmers' participation in collective marketing: micro-level evidence from Ehlanzeni, South Africa. Frontiers in Sustainable Food Systems, 9, 1567943.https://doi.org/10.3389/fsufs.2025.1567943

Mallick, S., Burman, R. R., Padaria, R. N., Mahra, G. S., Aditya, K., Shekhawat, K., ... & Mukherjee, S. (2025). Exploring farmers’ psychological perspectives on multimedia-based agro-advisory services. Scientific Reports, 15(1), 8898.https://doi.org/10.1038/s41598-025-92936-3

Pal P. K., Bhutia P. T., Das L., Lepcha N. &Nain M.S. (2017). Livelihood diversity in family farming in selected hill areas of West Bengal, India. Journal of Journal of Community Mobilization and Sustainable Development. 12(2),172-178.

Pani, B. S., & Mishra, D. (2022). Sustainable livelihood security in Odisha, India: A district level analysis. Regional Sustainability, 3(2), 110-121.https://doi.org/10.1016/j.regsus.2022.07.003

Panigrahi, S. P., Ghadei, K., Nikhil, J., Chennamadhava, M., Sethi, K., & Gupta, R. P. (2024). Construction and standardisation of agripreneurial performance scale. Indian Journal of Extension Education, 60(3), 88–92. https://doi.org/10.48165/IJEE.2024.603RT01

Prusty, A. K., Saha, P., Das, N., & Suman, S. (2025). Implementation and adoption of smart technologies in agri-allied sectors. Plant Science Today, 11(sp2), 3467. https://doi.org/10.14719/pst.3467

Rana, P., Fischer, H. W., Coleman, E. A., & Fleischman, F. (2024). Using machine learning to uncover synergies between forest restoration and livelihood support in the Himalayas. Ecology and Society, 29(1), 32. https://doi.org/10.5751/ES-14696-290132

Ruzzante, S., Labarta, R., &Bilton, A. (2021). Adoption of agricultural technology in the developing world: A meta-analysis of the empirical literature. World development, 146, 105599.https://doi.org/10.1016/j.worlddev.2021.105599

Ryo, M. (2022). Explainable artificial intelligence and interpretable machine learning for agricultural data analysis. Artificial Intelligence in Agriculture, 6, 257-265.https://doi.org/10.1016/j.aiia.2022.11.003

Saha, P., Prusty, A. K., Nanda, C., Ray, S., & Sahoo, B. (2024). Professional insights provided by women extension personnel in Odisha. Indian Journal of Extension Education, 60(3), 101–105. https://doi.org/10.48165/IJEE.2024.603RN03

Satapathy, G. P., Das, S., & Tripathy, M. (2024). Factors influencing ICT accessibility among the farming community of Odisha. Indian Journal of Extension Education, 60(2), 38–42. https://doi.org/10.48165/IJEE.2024.60207

Suman, S., Prusty, A. K., Deb, A., Kumari, A., & Reddy, G. S. (2025). Global research trends in family farming: A bibliometric insight. Indian Journal of Extension Education, 61(1), 25–31. https://doi.org/10.48165/IJEE.2025.61105

Zhang, X., Yang, Q., Al Mamun, A., Masukujjaman, M., & Masud, M. M. (2024). Acceptance of new agricultural technology among small rural farmers. Humanities and Social Sciences Communications, 11(1), 1-17.https://doi.org/10.1057/s41599-024-04163-2