International Journal Of Imaging

Abstract

STOCK TREND ANALYZER

Author: V. SRINIVAS, K. MANISHRAJ, KOMAL SUBRAMANYAM, LALU PRASAD, V JONAH CHETAN

Abstract:

In today’s fast-evolving technological landscape, accuratelypredictingmarkettrendsplaysacriticalrolein minimizing financial risks and maximizing potential returns. This work introduces a novel approach, the MS- SSA- LSTMmodel,designedtoharnessmulti-sourcedata in the prediction of stock prices. By incorporating sentiment analysis, swarm intelligence techniques, and deep learning, this method analyses data such as posts from theEast Moneyforum tocreate a custom sentiment lexiconandcalculatesentimentindices.Theseindicesare then integrated with traditional market data, with the Sparrow Search Algorithm (SSA) optimizing the parameters of a Long Short-Term Memory (LSTM) network.TheresultsshowthattheMS-SSA-LSTMmodel significantlyimprovesforecastingaccuracy,achievingan average R² increase of 10.74% compared to standard LSTM methods. Furthermore, the combination of sentiment indices and hyperparameter optimization enhances the model's performance, offering a robust solution forshort- t