Kotamsetty Geethika Devi , Bandi Rajeswara Reddy , Galeti Mohammad Hussain ¸ Gownivalla Siddartha 2 1 (January - March) Recent developments in complex machine learning models have drastically increased the accuracy of electricity price forecasting In this paper a combined model merging the RF and LSTM algorithms is given for improving price forecasting The stated model expands the ability of the RF algorithm to find advanced interactions between features and the ability of the LSTM algorithm to identify temporal dependencies in time series data The dataset set is of variables like demand temperature sunlight and rainfall Minmax scaling is applied to the preprocessing along with the sliding window technique Output describe that the combined hybrid model has improved accuracy than individual models with higher precision and recall values Specifically the hybrid model achieved 95 87 accuracy a precision of 0 88 a recall of 0 91 and an RMSE of 0 032 The standalone Random Forest model was able to reach an accuracy of 93 4 The LSTM model achieved an accuracy of 941 Further hybrid model further improved the performance results in terms of precision recall and RMSE Hence this shows that the combined model is better suited for the task of forecasting electricity prices which makes the hybrid model capable of delivering efficient realtime predictions required to make decisions in the energy markets The results of the output are such that it indicates hybrid models that integrate RF and LSTM could deliver more dependence and practicality insights Copyright (c) World Journal of Pharmaceutical Seiences. All rights reserved 2026