Datasets
Standard Dataset
Integrated Financial Dataset for Malayan Banking Berhad Stock Prediction
- Citation Author(s):
- Submitted by:
- Kar Hong Sam
- Last updated:
- Tue, 12/31/2024 - 02:27
- DOI:
- 10.21227/yq4t-mn93
- Data Format:
- License:
- Categories:
- Keywords:
Abstract
This dataset integrates financial and macroeconomic indicators to support research on stock price prediction and financial forecasting. It includes daily stock data for Malayan Banking Berhad (MBB) (1155.KL
) sourced from Yahoo Finance, alongside macroeconomic indicators such as GDP (constant 2015 MYR), GDP growth (YoY %), inflation rate (%), and the Overnight Policy Rate (OPR). The data spans a 20-year period from July 1, 2004, to August 1, 2024, and has been standardized to a daily frequency.
The dataset was meticulously preprocessed using Python, with missing values handled via forward or backward filling methods. Macroeconomic data was downloaded from the World Bank and BNM, while stock data was collected using the yfinance
library. Data alignment ensures consistency across all variables, making the dataset suitable for time-series analysis and machine learning applications.
This dataset is ideal for developing and evaluating deep learning models, such as LSTM and hybrid architectures, for financial forecasting. Researchers can leverage this resource to explore relationships between stock prices and macroeconomic indicators or to design innovative predictive models.
The dataset is licensed under the CC BY 4.0 and includes clear documentation on data preprocessing and sources. Proper attribution to Yahoo Finance, World Bank, and BNM is required when using this dataset.
Keywords: Stock Price Prediction, Financial Forecasting, Time-Series Analysis, Deep Learning, Macroeconomic Indicators, Malaysia
Overview
This dataset integrates stock data for Malayan Banking Berhad (MBB) with macroeconomic indicators to facilitate research on financial forecasting and time-series analysis. It provides preprocessed, standardized data ready for machine learning and statistical analysis.
Dataset Files
The uploaded dataset includes the following files:
- mbb_financial_dataset.csv: The main dataset containing daily financial and macroeconomic indicators.
- README.md: A detailed description of the dataset, its sources, and the preprocessing steps.
Using the Dataset
-
Download:
- Access the dataset files through the "Download" section on this page.
-
Understand the Structure:
- The main dataset (
mbb_financial_dataset.csv
) contains the following columns:date
: Standardized daily dates (2004-07-01 to 2024-08-01).Open
,High
,Low
,Close
,Adjusted Close
,Volume
: Daily stock data from Yahoo Finance.GDP (constant 2015 MYR)
: GDP data converted from USD to MYR (sourced from World Bank).GDP Growth YoY (%)
: Year-over-year GDP growth rates.Inflation Rate (%)
: Monthly inflation rates (%).OPR (%)
: Monthly Overnight Policy Rate data from Bank Negara Malaysia.
- For further details, refer to the
README.md
.
- The main dataset (
-
Run Analysis:
- Use this dataset for tasks such as:
- Financial forecasting using machine learning or deep learning models (e.g., LSTM).
- Statistical analysis of relationships between stock prices and macroeconomic indicators.
- Exploratory data analysis (EDA) to derive insights into stock and macroeconomic trends.
- Use this dataset for tasks such as:
Attribution
If you use this dataset, please acknowledge the original sources:
- Yahoo Finance for stock data.
- Bank Negara Malaysia (BNM) for OPR data.
- World Bank DataBank for macroeconomic indicators.
Include the following citation:
Dataset created by Sam Kar Hong, GitHub Profile, 2024. Licensed under CC BY 4.0.
Licensing
This dataset is licensed under the CC BY 4.0. You are free to use, modify, and distribute the dataset, provided proper attribution is given and the license terms are followed. See the LICENSE
file for full details.
Contact
For questions or further assistance, please contact:
Sam Kar Hong
GitHub Profile: @karhong-sam