In today’s market, predicting agricultural product prices on time and with reliability is critical. Forecasting prices for agricultural commodities is challenging due to multiple contributing factors. The unpredictability of future prices, production capacities, and demand trends makes market strategy and investment planning more challenging. This study analyzes and forecasts trends in tomato pricing using linear, quadratic, and exponential trends. In the domain of agricultural product price prediction, models such as autoregressive integrated moving average, autoregressive conditional heteroskedasticity/generalized autoregressive conditional heteroskedasticity, temporal fusion transformer, and Prophet are utilized. Temporal fusion transformer and Prophet models are employed to analyze the seasonal impact on the tomato price dataset. To improvise the price prediction performance, the Prophet model is used along with the temporal fusion transformer model in the proposed system. Performance of the models is compared statistically using mean absolute error, symmetric mean absolute percentage error, and root mean square error. The proposed Prophet with temporal fusion transformer model shows superior performance by achieving a SMAPE of 22.03, an MAE of 328.11, and an RMSE of 790.11 in the tomato price forecast.