The application of Neural Prophet Time Series in predicting rice stock at Rice Stores

Efficient inventory management and consistent rice supply are pivotal for the sustainability of small-scale food stalls. This research introduces an innovative approach to address this challenge through Neural Prophet algorithm. By synergizing neural networks with additive regression models, captures intricate temporal patterns trends within sales data. Our study evaluates Prophet's effectiveness in predicting sales, specifically essential vendors. Leveraging historical data from June 2022 April 2023, algorithm incorporates seasonality integrates external events, such as holidays, heighten prediction precision. findings underscore remarkable prowess forecasting at primary kiosks, adeptly discerning fluctuations, culminating reliable future projections. The model boasts compelling performance metrics: MAE = 12.90, RMSE 15.80, Loss 0.0313. Beyond its technical merits, carries significant practical implications, empowering proprietors suppliers basic stalls streamline management, avert stockouts, curtail overstocking by harnessing precision demand facilitated