Project Overview
This advanced data analysis project delves into the financial performance of four major banks by examining their daily stock data, sourced from Stooq. The primary objective was to apply sophisticated data analysis and visualization techniques to financial datasets, with the aim of uncovering critical insights that could inform investment strategies and financial decision-making.
In this analysis, I focused on:
- Daily opening and closing stock prices
- Trading volumes for each bank
- Maximum closing values and other key financial metrics
- Trends and patterns in stock performance over time
By understanding these financial metrics and trends, the analysis provides valuable insights into the stock performance and market behavior of the banks, aiding in more informed financial planning and investment decisions.
Dataset Description
The analysis uses a dataset containing 10 years of daily stock data for four major banks, sourced from Stooq. The dataset includes the following key features:
Stock Prices
Daily opening, closing, high, and low prices for each bank's stock, providing a comprehensive view of stock performance over time.
Trading Volume
The number of shares traded each day, which helps in understanding the liquidity and trading activity of the stocks.
Adjusted Close Price
The closing price adjusted for dividends and stock splits, offering a more accurate reflection of the stock's value over time.
Date Information
Timestamps for each trading day, allowing for time-based analysis of stock performance and trends.
Methodology
The analysis followed a structured approach to extract meaningful insights from the financial dataset:
Step 1: Understanding the Data
Initial exploration to identify the structure, missing values, and key features available in the dataset. Grouped stock data by bank to find performance trends.
Step 2: Feature Extraction
Created new features like 'daily_return' by calculating the percentage change in closing prices. This helped in assessing daily stock performance.
Step 3: Time-Based Analysis
Converted timestamps to datetime objects and extracted month and year information to analyze temporal patterns in stock performance.
Step 4: Risk Assessment
Calculated the standard deviation of daily returns to assess the riskiness of each stock. Higher standard deviation indicated higher volatility.
Step 5: Visualization
Used Seaborn, Matplotlib, and Plotly to create informative visualizations that revealed patterns and trends in the financial data.
Key Visualizations
Candlestick Chart for Bank of America
Stock Performance Over the Years
Key Findings
Stock Volatility
Bank stocks exhibited varying levels of volatility, with some showing higher fluctuations in daily returns, indicating higher risk.
Trading Volume Trends
Significant patterns in trading volumes were observed, with certain periods showing spikes in activity, possibly due to market events or earnings reports.
Seasonal Effects
Stock performance showed seasonal trends, with certain months exhibiting stronger performance, potentially linked to broader economic cycles.
Comparative Analysis
Comparing the four banks revealed differences in stock performance and risk profiles, providing insights into their market positioning.
Correlation Analysis
Analyzed correlations between the banks' stock prices, identifying potential co-movements and diversification opportunities.
Data Science Capstone Project | Created for Portfolio Showcase
Analysis completed using Python, Pandas, Matplotlib, Seaborn, and Plotly