Agricultural commodity price prediction helps the government, investors, and farmersrnto make informed decisions. Realizing the benefit, several researchers proposed differentrnprediction models that use different features. However, most prediction models arernaffected by factors, such as data type (e.g., linear and nonlinear), seasonality of commodityrnitems, weather conditions, commodity volatility features, and country economicrnfactors. Among these factors, the most significant impediments to the accuracy of commodityrnprice prediction are seasonality and trend pattern. To fill this gap, we proposerna model that predicts commodity prices through the combination of time series featuresrnand technical indicators. The prediction model is built using four-machine learning algorithms:rnArtificial Neural Network, Extreme Learning Machine, Support Vector Machine,rnand Random Forest. To assess the impact of the proposed approach, we conducted twornexperiments using coffee and sesame datasets. The performance of the prediction modelsrnis assessed using the root mean square error (RMSE) and mean average error (MAE). Thernresults show that the proposed approach improves agricultural commodity price predictionrnperformance in all cases except MAE of sesame while using Extreme LearningrnMachine. Using Artificial Neural Network, Extreme Learning Machine, Support VectorrnMachine and Random Forest, the RMSE of price prediction is reduced by an average ofrn4.37, 4.42, 2.74, and 5.15, respectively. Finally, among the four machine learning algorithmsrnused in the study, Artificial Neural Network is found to be the best algorithm forrnenhancing the performance of agricultural commodity price prediction. We also concludernfrom our experiment result that considering commodity properties such as periodicity,rnvolatility, linearity, momentum, volume, and trend would improve the performance ofrnagricultural commodity price prediction. To see which of the features contributed morernto the improvement of agricultural commodity price prediction, we computed feature importancernusing Random forest algorithms. The result shows that: close, high, low, open,rnexponential moving average (EMA), double exponential moving average (DEMA), simplernmoving average (SMA), truehigh, truelow, trend, seasonality, relative strength indexrn(RSI) are the most important features in sesame and coffee price prediction.