Predictive analytics in Agriculture: Forecasting prices of Arecanuts in Kerala

• Published in: Procedia computer science Vol. 171; pp. 699 - 708
• Main Authors: Sabu, Kiran M., Kumar, T.K. Manoj
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 2020
• Subjects: Holt-Winter’s Seasonal method; LSTM; Predictive analytics; RMSE; SARIMA; Holt-Winter’s Seasonal method; LSTM; RMSE; SARIMA; Predictive analytics
• ISSN: 1877-0509; 1877-0509
• DOI: 10.1016/j.procs.2020.04.076

The fluctuations in prices of agricultural commodities have an adverse effect on the GDP of a country. The farmers are emotionally and financially affected as their years of hard work go in vain. Prediction of the prices may help the agriculture supply chain in making necessary decisions in minimizing and managing the risk of price fluctuations. As a result of the reduction in agricultural production due to unstable climatic conditions, global warming etc., predictive analytics is expected to solve the problems of the common man. Arecanut is an important crop cultivated in India, with Kerala being second in terms of production. In recent years farmers in Kerala are shifting from arecanut cultivation to other crops because of price fluctuations and climate change. In this work, the monthly prices of arecanut in Kerala are predicted using time-series and machine learning models. The models SARIMA, Holt-Winter’s Seasonal method, and LSTM neural network were used, and their performance was evaluated based on the RMSE value on the arecanut dataset with prices from 2007 to 2017. LSTM neural network model was found to be the best model that fits the data.