Artificial Intelligence methods for decision making

Gaurav Keshavkumar Patel

Master's thesis

Abstract:

Artificial Intelligence methods are used for decision making in Stock Market Prediction and Efficiency Analysis using Recurrent Neural Network and with Python. Forecasting stock market prices have always been challenging task for many businesses analyst and researchers. In fact, stock market price prediction is an interesting area of research for investors. For successful investment, many investors are interested in knowing about the future situation of the market. Based on the study's key findings, the research with respect to the assessment and help to prediction regarding the use of stock markets has been found very promising using various artificial intelligence methods for decision making. In this project, we study the problem of stock market forecasting using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM). The purpose of this project is to examine the feasibility and performance of LSTM in stock market forecasting. There are also some significant implications reported that need to be further analyzed in continuing the approach. The trading associated with stock markets has been found convincing and positive in recent times as different tools discussed in the methodology section were found effective in determining the efficiency and predictors of the stock market. Using Kaggle to collect the Google dataset was convincing, based on relevant results generated. Thus, the study aims to use a primary dataset throughout the project due to convincing and satisfying results. The major recommendation regarding this project was to contain the daily change in ratios of stock price by storing it in a CSV file. The storing of data in this file would be helpful in making the import and export of data easier in Python. The stock sector is one of the widely spread sectors in the world. The different functions included in the stock are bonds, stocks and other agreements between buyers and sellers. With the generation of promising results from the findings and analysis, there are some limitations or implications observed during the study. With their ability to discover patterns in nonlinear and chaotic systems, neural networks offer the ability to predict market directions more accurately than current techniques which helps the investor to make the better decision making in stock market.

Keywords

Neural networks, Machine learning, Decision Making, Artificial Intelligence, Stock Prediction

Language used: English

Date on which the thesis was submitted / produced: 14. 3. 2022

Thesis defence

• Supervisor: doc. Ing. Arnošt Veselý, CSc.
• Reader: Richard Vágner, externi

Czech University of Life Sciences Prague

Faculty of Economics and Management

Master programme / field:
Systems Engineering and Informatics / Informatics