International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 186 - Number 64 |
Year of Publication: 2025 |
Authors: Komal Batool, Ubaida Fatima, Mirza Faizan Ahmed |
![]() |
Komal Batool, Ubaida Fatima, Mirza Faizan Ahmed . Trend Prediction of DJIA index based on News Extraction from Yahoo Finance. International Journal of Computer Applications. 186, 64 ( Feb 2025), 42-46. DOI=10.5120/ijca2025924379
Decision making in a financial world is a very challenging task for any investor as it can leads towards a very heavy loss as well as very higher returns. Therefore, proper understanding of market behavior is required. It is found in research that movement of prices in financial market is random in nature and depends on multiple factors. In this research sentiment-based prediction of DJIA (Dow Jones Industrial Average) index is performed to forecast the future direction of the indices. The objective behind this research is to analyze if the market is sensitive to news or not and if the web news data contributes in the movement of the market. Five different classification models of machine learning are used which include decision tree, random forest, support vector machine, K-Nearest Neighbor and logistic regression. It is observed that KNN is the best predictive model among all for our dataset with the accuracy of 70%. The results are validated on NASDAQ composite and proved that KNN outperforms other considered classifiers.