STM Journals Peer-reviewed research from Consortium e-Learning Network

E-Commerce for Future & Trends

Stock Price Prediction Using Data Science Techniques

  1. P. Kavipriya
  2. Yerukala Chandrasekhar
  3. Paluri Chandrasekhar Pavan

Abstract

This study centers around persuasively presenting the potential to forecast the stability of future market stocks. Previous research has delved into predicting the trajectory of future market trends, leading to fluctuations in stock data, which opens avenues for refinement. The proposed model employs data science methodologies to predict the stock price index's value. This is achieved by contrasting supervised classification data science learning algorithms that predict either stock price increases or stable states. Furthermore, the research aims to differentiate and meticulously analyze the effectiveness of diverse data science algorithms, utilizing data from the transportation traffic department. To gauge the proposed data science approach's effectiveness, the investigation utilized techniques such as constructing a confusion matrix, assigning significance to data classification, and benchmarking the outcomes against optimal precision, recall, and F1 scores.

Keywords

Support