What is it about?
The paper focuses on predicting the Nifty 50 Index by using 8 Supervised Machine Learning Models. The techniques used for empirical study are Adaptive Boost (AdaBoost), k-Nearest Neighbors (kNN), Linear Regression (LR), Artificial Neural Network (ANN), Random Forest (RF), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM) and Decision Trees (DT). Experiments are based on historical data of Nifty 50 Index of Indian Stock Market from 22nd April, 1996 to 16th April, 2021, which is time series data of around 25 years. During the period there were 6220 trading days excluding all the non trading days. The entire trading dataset was divided into 4 subsets of different size-25% of entire data, 50% of entire data, 75% of entire data and entire data. Each subset was further divided into 2 parts-training data and testing data. After applying 3 tests- Test on Training Data, Test on Testing Data and Cross Validation Test on each subset, the prediction performance of the used models were compared and after comparison, very interesting results were found. The evaluation results indicate that Adaptive Boost, k- Nearest Neighbors, Random Forest and Decision Trees under performed with increase in the size of data set. Linear Regression and Artificial Neural Network shown almost similar prediction results among all the models but Artificial Neural Network took more time in training and validating the model. Thereafter Support Vector Machine performed better among rest of the models but with increase in the size of data set, Stochastic Gradient Descent performed better than Support Vector Machine.
Featured Image
Photo by Stephen Dawson on Unsplash
Why is it important?
Prediction of the movements of the stock market index is very important for developing the effective market trading strategies. Financial decision to buy or sell an instrument may be made by the traders by choosing the effective predictive model. Successful prediction of Stock Market Index movements may be beneficial for investors. The tasks of predicting the movements of the Stock Market Index are highly complicated and very difficult. This empirical study attempted to predict the direction of Nifty 50 Index movement in the Indian Stock Market. Eight prediction models were constructed and their performances were compared on historical data from April 22, 1996 to April 16, 2021.
Perspectives
Based on the experimental results obtained, some important conclusions can be drawn. Linear Regression and Artificial Neural Network performed almost equal performance in all the segments of different size of data. The reason behind good performance by Linear Regression competing to Artificial Neural Network was that regression method deals better with linear dependencies whereas neural networks can deal better with non linear dependencies. So if the data will be having some non linear dependencies, Neural Networks should perform better than regression. After LR and ANN, Support Vector Machine performed well but with increase in the size of data Stochastic Gradient Descent performed better than SVM. Thereafter ensemble learning methods of Decision Tree- AdaBoost and Random Forest performed better than kNN and Decision Tree with increase in the size of data. In this empirical study eight Supervised Machine Learning Models were used, in future empirical study, more ensemble methods for Supervised Machine Learning Models can be taken. This empirical study used around 25 years historical data, which is good for machine learning because in such a long period many bull and bear phases of stock market were included.
Dr. Gurjeet Singh
Read the Original
This page is a summary of: Machine Learning Models in Stock Market Prediction, International Journal of Innovative Technology and Exploring Engineering, January 2022, Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP,
DOI: 10.35940/ijitee.c9733.0111322.
You can read the full text:
Resources
Contributors
The following have contributed to this page
