This study employs Support Vector Machine (SVM) analysis to assess agricultural productivity in Tamil Nadu, India. SVM, a powerful machine learning technique, is utilized to analyze diverse agricultural datasets encompassing crop yields, climatic factors, soil properties, and socioeconomic indicators. The SVM model is trained to predict and evaluate agricultural productivity based on historical data, providing insights into the factors influencing crop performance in the region. Results highlight the effectiveness of SVM in identifying critical variables affecting agricultural outcomes and offer valuable insights for policymakers and agricultural stakeholders aiming to enhance productivity and sustainability in Tamil Nadu.

Support Vector Machine (SVM), Agricultural productivity, Crop yields

Anderson TW (1984) An Introduction to Multivariate Statistical Analysis, 2/e, John Wiley and Sons, Inc., New York.

Jasbir Singh, Dhillon S S (2002) Agricultural Geography, Tata McGraw Hill Publishing Company Limited, New Delhi.

Kalpana Sahoo, Narayan Sethi (2012) Investigating the impact of Agriculture and Industrial Sector on Economic Growth of India. OIDA International Journal of Sustainable Development 05:05, pp. 11-22.

Kohonen T (2001), Learning vector quantization. Springer, Berlin Heidelberg.

Manimannan G. et.al. (2016), Classification of agricultural productivity index of Cauvery delta zone using artificial neural network, Agriculture Science Digest, A Research Journal, India, pp. 1-6.

Han, J., Kamber, M. 2012. Data Mining: Concepts and Techniques, 3rd ed, 443-491.

Shafi M (1983) Agricultural Productivity and Regional Imbalances – A study of Uttar Pradesh. Concept Publishing Company, New Delhi.

Season and Crop Report, Tamilnadu (Various Issues), published by Department of Economics and Statistics, Chennai.

Statistical Hand Book of Tamilnadu (2012-2013), Department of Economics and Statistics, Chennai.