The week's pick
Reseach Article
Comparison of HDNN with other Machine Learning Models in Stock Market Prediction
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 182 - Number 1 |
| Year of Publication: 2018 |
| Authors: Vaibhav Kumar, M. L. Garg |
10.5120/ijca2018917430
|
Vaibhav Kumar, M. L. Garg . Comparison of HDNN with other Machine Learning Models in Stock Market Prediction. International Journal of Computer Applications. 182, 1 ( Jul 2018), 1-9. DOI=10.5120/ijca2018917430
Abstract
A hybrid deep learning model has been developed in this research which is the combination of a deep neural network and the fuzzy inference system. This model is termed in this paper as Hybrid Deep Neural Network (HDNN). In this model, we have integrated the Sugeno fuzzy inference system with the deep neural network. This model has been used in the task of stock market prediction. Through this model, the day’s closing price of a stock has been predicted on the basis of certain factors as parameters which affect the price of a stock. We have tested our model in the prediction of seven stocks and compared the result of prediction with popular similar models. It was found that the HDNN model has the best performance in this task. In This paper, we will present the comparison of HDNN model with five other machine learning models- Generalized Linear Model (GLM), Multilayer Perceptron (MLP), Gradient Boost Model (GBM), Random Forest Model (RF) and the Deep Neural Network (DNN).
References
- . J W Lee, 2001, “Stock price prediction using reinforcement learning”, Proceedings of the IEEE International Symposium on Industrial Electronics, Pusan, South Korea.
- . L Pastor, P Veronesi, 2009, “Technological Revolutions and Stock Prices”, American Economic Review, Vol-99, Issue-4, Pages- 1451-83.
- . A Yoshihara, K Fujikawa, K Seki, K Uehara, 2014, “Predicting Stock Market Trends by Recurrent Deep Neural Networks”, Proceedings of the Pacific Rim International Conference on Artificial Intelligence, Pages- 759-769.
- . K Chen, Y Zhou, F Dai, 2015, “A LSTM-based method for stock returns prediction: A case study of China stock market”, Proceedings of the IEEE International Conference on Big Data, CA, USA.
- . Shoichi Eguchi, “Model Comparison for generalized linear models with dependent observations” (2017), Econometrics and Statistics, Vol-59.
- . John Nelder, Robert Wedderburn, (1972), “Generalized Linear Models”, Journal of Royal Statistical Society.
- . Frank Rosenblatt, (1961), “Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms”, Spartan Books.
- . David Rumelhart, Geoffrey Hinton, R. J. Williams, (1986), “Learning Internal Representations by Error Propagation”, Parallel Distribute Processing: Explorations in the microstructure of cognition, Vol-1.
- . Varun Kumar Ojha, Ajith Abraham, Vaclav Snasel, (2017), “Metaheuristic design of feedforward neural networks: A review of two decades of research”, Engineering Applications of Artificial Intelligence, Vol-60.
- . Simon Haykin, (2012), “Neural Networks: A comprehensive Foundation”, 2nd Edition, Prentice Hall.
- . Ji Kan, (2017) , “Evaluation of Mining Engineering technology innovation ability and application based on BP neural network”, International Conference on Industrial Technology and Management (ICITM).
- . Yanru Zhang, Ali Haghani, (2015), “A gradient boosting method to improve travel time prediction”, Transportation Research, Part C.
- . J. H. Friedman, (1999), “Greedy Function Approximation: A Gradient Boosting Machine”.
- . Tin Kam Ho, (1995), “Random Decision Forests”, 3rd International Conference on Document Analysis and Recognition, Montreal.
- . Tin Kam Ho, (1998), “The Random Subspace Method for Constructing Decision Forests”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol-20.
- . Tin Kam Ho, (2002), “A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructions”, Pattern Analysis and Applications.
- . J. Schmidhuber, “Deep Learning in Neural Networks”, Technical Report IDSIA-03-14 arXiv: 1404.7828.
- . J. Schmidhuber, (2001), “LSTM Recurrent Networks Learn Simple Context Free and Context Sensitive Languages”, IEEE Transaction on Neural Networks, Vol-12.
Index Terms
Keywords