NORMA eResearch @NCI Library

Analyzing and predict stock prices: Technical Report

Iqbal, Umer (2021) Analyzing and predict stock prices: Technical Report. Undergraduate thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Bachelor of Science)
Download (4MB) | Preview

Abstract

A company stock price is the highest amount someone is willing to pay for the stock, or the lowest amount that it can be bought for. Technical analysis can be used to predict information on future price movements from historical data.

The project aims to Analyse and predict the historical stock prices of Amazon and Apple Inc etc. In the beginning, the introduction of the project is explained including background, aim, and technology. After that project report briefly discussed the complexity of data, how datasets were acquired/obtained, why datasets are suitable for my project, how datasets are complemented with each other, and characteristics of our datasets, what data visualisations tools were used. Next, we have the KDD methodology section which described a selection of our data, preprocessing/cleaning methods, a transformation of our data, data mining/Machine learning technique (LSTM, ARIMA forecasting, random forest, decision trees, kMeans clustering, hierarchical Clustering, etc.), and evaluation process. Following, project report contains a brief explanation of analysis how datasets were used for pre-processing/cleaning a brief discussion on LSTM, ARIMA forecasting, steps involved during implementation and why these steps were carried out for implementations, characteristics of analysis, advanced statistics (descriptive statistics, Kruskal Wallis test, Mann Whitney test, normality test and Wilcoxon signed-rank test), exploratory data analysis, why did I choose closing price attributes for predicting my stocks values as a predictor in my model. Afterward, all outputs are explained in the results section, describing results tables and figures.

Data visualizations and principal component analysis etc. techniques are used to explore the datasets. Long short term memory and ARIMA forecasting were used to develop models for the prediction of stock prices. Is it going to increase or decrease in stock prices of Apple Inc and Amazon? Keras, TensorFlow and forecasting packages were used for the smooth development of the prediction model.

Item Type: Thesis (Undergraduate)
Subjects: H Social Sciences > HA Statistics
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

H Social Sciences > HG Finance > Investment
Divisions: School of Computing > Bachelor of Science (Honours) in Computing
Depositing User: Clara Chan
Date Deposited: 02 Sep 2021 10:20
Last Modified: 20 Sep 2021 09:50
URI: http://norma.ncirl.ie/id/eprint/5000

Actions (login required)

View Item View Item