Loading...

Providing a Method Based on Signal Transformations and Machine Learning Tools for Forecasting in Stock Market

Parhizkari, Amir | 2019

521 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52348 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Khedmati, Majid
  7. Abstract:
  8. Obtaining high profit is the ultimate goal of an investor in the financial market. The key to achieve high profits in stock trading is to find the right time to trade with minimum business risk. However, it is difficult, often, to make decision about the best time to buy or sell some stocks due to the extremely dynamic and volatile behavior of the stock market. In order to resolve these problems, two steps have been followed in this research:1) Create a model to predict the final price of the stock with small error rate, and 2) Suggest the best stocks for trading to the trader. In order to achieve the goals of the first step, the stock price data of Hcltech, Maruti, Axisbank is selected and signal transformations and long-short term memory (LSTM) have been used to predict the stock prices. Then, the results have been evaluated according to the mean absolute percentage error (MAPE) and confusion matrix criteria. Also, in this stage, in order to evaluate the performance of the proposed model, the shares of 15 companies including Apple and Google stocks have been evaluated by the model. Finally, to achieve the second objective, a specific strategy with Bayesian optimization algorithm has been used, In this strategy, we determine the initial capital of the trader along with how to buy or sell in terms of shares to be traded, and as an output we obtain the percentage of profit earned from trades to evaluate the algorithm. Based on the results, it has been shown that the algorithm has acceptable performance in terms of the error rate. Then, it has been applied to choose the right stock, among the three stocks, for trading where the stocks of Axisbank have been selected in the period under consideration
  9. Keywords:
  10. Stock Price ; Stock Selection ; Price Forecasting ; Long Short Term Memory (LSTM) ; Bayesian Optimization ; Signal Transformations

 Digital Object List

 Bookmark

No TOC