Loading...

Capital Market Forecasting with Machine Learning Model and Comparing it with Forecasting Using System Dynamic

Kazem Dehbashi, Sina | 2020

530 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53218 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Kianfar, Farhad
  7. Abstract:
  8. Prediction is an important issue in many areas. Proper planning for the future requires careful forecasting, so providing accurate methods, especially in the financial field, is invaluable. In this study, the main problem is predicting the price of global gold. Factors for gold prices include oil, gas, silver, soybeans, copper, the s & p500 index, the Dow Jones index, the British and Japanese stock market indices, the dollar index, the multi-currency exchange rate (pound-euro-yuan-yen) with the dollar to The title of the influential factors in this research is considered. The time frame of this research is daily, in other words, the data is collected on a daily basis and the goal is to predict the price of gold in the future. In this research, machine learning and system dynamics topics have been used. The machine learning method uses support vector machine algorithms with polynomial kernel, the nearest neighbors, a random forest, and an artificial neural network (MLP). It should be noted that in addition to the independent use of algorithms, a hybrid model was finally created by combining them, which showed a very good performance. On the other hand, the price of gold is a random process and random systems have been used to predict it. In order to predict, the gold price process is first modeled by the average moving average (ARIMA) autoregression method and then its performance in the forecast is evaluated. Finally, the results of each of the algorithms and models were examined. In the end, the best performance belonged to the hybrid model
  9. Keywords:
  10. Machine Learning ; Stochastic Systems ; Nearest Neighbor ; Artificial Neural Network ; Support Vector Machine (SVM) ; Autoregressive Integrated Moving Average (ARIMA) ; Random Forest Algorithm ; Gold Price Prediction

 Digital Object List

 Bookmark

No TOC