Enhancing agriculture supply chains through regional demand forecasting with Machine Learning Algorithms

Shivendra  Singh; Tushar  Suthar; Mira  Gohil

Abstract

With the stats analysis of 2014 of Our Country Agricultural supply chain faces a significant inefficiencies as the intermediate stakeholders capture the large portion of the value, in this scenario farmers only earn about 31 to 43 percent of final market price. This imbalance contributes to higher consumers expenditures and unequal income distribution and substantial post harvest waste. To tackle these challenges this research introduces kisaankart which is a machine learning- driven a digital framework that is designed to enhance the demand prediction accuracy and make transparent fair pricing between farmers and consumers connectivity. This approach explore the potential of artificial intelligence models check price forecasting and market trends analysis. By Using govt mandi prices data, simulated orders and users interaction records, and preprocessing and feature engineering are applied to both categorical and temporal variables. The performance of some machine learning like ARIMA, XGBOOST, and LSTM/GRU are used assessed through RMSE and MAE comparison supported by pilot feedback and cross validation and for model validation and measurement of user responses. Resulting indicates that ML based system outperform traditional stats models in identifying the some complex seasonal and market dynamics. With the Additional the hybrid recommended engine significantly enhances users engagement metrices such as click through the conversion rates. Simulations of market outcomes suggest that direct digital trade could raise farmers earning by 25 to 35 and reduced in consumers prices by 15 to 25 percent, So Overall, kissankart demonstrate that implementing of machine learning and real world validation are recommended to enhance scalability and long term sustainability in transforming Indias Agriculture value network.

Abstract

Keywords