Stock prices prediction : a comparative analysis of traditional financial models, neural networks and facebook prophet library | |
| Author | Ali, Adnan |
| Call Number | AIT Thesis no.IM-21-01 |
| Subject(s) | Stock price forecasting--Developing countries--Mathematical models Neural Networks Machine learning |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | Stock market is a place where investors can invest impartially and get profit/loss. To predict the stock market prices is a challenge for all the stakeholders as data is in the form of time series, highly fluctuated, complex, nonlinear and volatile. The overall objective of this study is to conduct a comprehensive comparative analysis of predictive accuracy of traditional financial models, neural network model, and facebook prophet library. All of models predicted the monthly opening price of the stock. Our methodology consists of five steps: data collection, preprocessing and analysis then implementation and development of web application. Selected models are applied on technical, financial and macroeconomic variables on three different companies: Cherat cements, International steels, Oil and Gas development company of Pakistan Stock Exchange. Technical variables - open, close, high, low price are same for all companies, where financial variables are different as per availability of selected company data. Macroeconomic variables - money supply, open price dollar rate, treasure bills, inflation GDP are same for all companies. Data analysis revealed that SARIMAX model performed better than other models on the basis of MSE & RMSE. We could not find any significant impact of selected macroeconomic variables on stock companies prices. |
| Year | 2021 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Vatcharapron Esichiakul |
| Examination Committee(s) | Dailey, Matthew N.;Chaklam Silpasuwanchai |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2021 |