Minor Project
Minor Project
Name of Projectees
Introduction
Justifications for Selecting the Title
Problem Statement
Literature Survey
Block Diagram
Expected Result
Work plan
References
Introduction
1) Stock market prediction is the act of trying to determine the future value of a company stock or
other financial Instrument traded on an exchange.
2) The successful prediction of a stock's future price could yield significant profit.
3) It involves analyzing various data points, historical trends, and using different methodologies,
including statistical analysis, technical analysis, fundamental analysis, and machine learning, to make
predictions about how stock prices are likely to behave in the future.
4) It's important to note that while stock market prediction is a valuable tool for investors and traders, no
method can provide 100% accuracy.
5) Markets are influenced by a wide array of variables, and unexpected events can occur. Therefore, it's
essential to use predictions as one element of a broader investment strategy and to diversify
investments to spread risk.
Justification For Selecting The Title
Selecting a stock prediction project can be a significant undertaking, and it's essential to provide a strong
justification for choosing such a project, especially if it's for academic or professional purposes. Here are
several reasons why you might choose to undertake a stock prediction project:
Relevance: The stock market plays a pivotal role in the global economy, and many individuals and
institutions invest in stocks as a means of wealth creation and financial security. Accurate stock predictions
can potentially lead to significant financial gains, making this project highly relevant.
Real-World Application: Stock prediction is a practical and real-world application of data analysis and
machine learning techniques. The skills and knowledge gained from this project are directly transferable to
various industries and job roles, making it a valuable learning experience.
Data Availability: There is an abundance of historical stock market data available, which facilitates the
development and testing of predictive models. This availability of data makes stock prediction an accessible
and feasible project for aspiring data scientists and analysts.
Problem Statement
Objective
Develop a machine learning model to predict stock prices for a given company based on historical data.
Model Training: Training the selected model on historical data. Implementing necessary strategies for dealing with stock
market anomalies like splits and dividends.
Data Preprocessing: Cleaning and handling missing data. Feature selection and engineering, including creating relevant
technical indicators. Splitting
data into training and testing sets.
Evaluation: Assessing the model's accuracy and performance using appropriate metrics (e.g., Mean Absolute Error, Root Mean
Squared Error).Conducting backtesting on historical data to evaluate trading strategies based on predictions.
Literature Survey
Sr. No. Paper Title and its Author Details of Publication Findings
Machine learning techniques and data for stock Technical Indicators (e.g., North American market
market forecasting return, simple moving covered most, especially the
1
average, RSI) common S&P500 index, followed by
Mahinda Mailagaha Kumbure predictors. Asia.
Financial time series forecasting with deep learning Which DL models are used for There ability to capture
2 financial time series complex patterns and
Omer Berat Sezer forecasting dependencies in the data.
Block Diagram
Expected Result
Predictive Accuracy: The primary expected result is accurate stock price predictions. The
extent of accuracy can vary, but ideally, the models should perform significantly better
than random guessing.
Feature Importance: If applicable, insights into the most influential features or variables
affecting the stock price predictions. This information can be valuable for understanding
the drivers behind price movements.
Work – Plan
August’23 Sept’23 Oct’23
Months Activities Nov’23
Literature Reviews √
Requirement Analysis √
Designing √
Experimental Analysis √ √ √
Module wise Implementation √ √
Testing and Debugging √ √
Preparation of Project Report √
References
Websites:
Kaggle:
https://www.kaggle.com/
QuantConnect:
1.https://www.quantconnect.com/
Investopedia
https://www.investopedia.com/
Book:
"Python Machine Learning" by Sebastian Raschka and Vahid Mirjalili
Thank you !