Stock Price Prediction - Tesla

---

Check out the code notebook for more details! Stock Price Prediction
Dataset link: TSLA.csv

Project Context

This project was developed as part of the Artificial Intelligence and Machine Learning Academy following my participation in the Ford Otosan "Gelecek Hayalim" Project. Through this program, I gained hands-on experience and mentorship, which significantly contributed to the successful implementation of the stock price prediction model.

Project Overview

This project aims to predict Tesla's stock prices using various machine-learning models. By utilizing historical stock price data, we built a predictive model to analyze whether it is beneficial to buy Tesla stock based on its predicted future prices. The project focuses on feature engineering and hyperparameter optimization to improve the accuracy of the model.

Key Features

• Stock Price Prediction: Predicted Tesla's stock prices using various machine learning models.
• Exploratory Data Analysis (EDA): Analyzed the dataset to identify trends, patterns, and potential issues with the data.
• • Data Visualization: Visualized stock price trends and prediction results using Matplotlib and Seaborn.
• Machine Learning Models: Utilized models such as Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost for predictions.
• Feature Engineering & Hyperparameter Tuning: Focused on enhancing the model's accuracy using feature engineering and hyperparameter optimization techniques.

Technologies Used

• Programming Language: Python
• Libraries & Frameworks:
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib
  • Seaborn
• Algorithms:
  • Logistic Regression
  • Random Forest
  • Support Vector Machine (SVM)
  • XGBoost
• Techniques:
  • Feature Engineering
  • Hyperparameter Optimization

Dataset

The dataset used in this project was obtained from Kaggle and contains Tesla stock price data from 2010 to 2022. This dataset includes the following columns:

• Date: Date of the stock data entry.
• Open: Opening stock price.
• High: Highest stock price of the day.
• Low: Lowest stock price of the day.
• Close: Closing stock price.
• Volume: Number of shares traded.
• Adj Close: Adjusted closing price.

Project Workflow

1. Data Collection: The historical stock price data for Tesla was collected from Kaggle.
2. Exploratory Data Analysis (EDA): Analyzed the dataset to identify trends, patterns, and potential issues with the data.
3. Preprocessing: Data was cleaned and prepared for training the models.
4. Feature Engineering: Key features were selected and engineered to improve model performance.
5. Model Training & Evaluation: Various machine learning models were trained, evaluated, and optimized for accuracy.
6. Prediction: The best-performing model was used to predict future stock prices.

Installation

1. Clone this repository to your local machine:

   git clone https://github.com/gamzegenc99/Stock_Price_Prediction.git

2. Install the required dependencies:

   pip install -r requirements.txt
   

How to Use

1. Open the Stock_Price_Prediction.ipynb file in Jupyter Notebook.
2. Run the cells sequentially to preprocess the data, train the models, and view the results.
3. Modify the input parameters and data as needed to experiment with different configurations.

Contributors

• Gamze Genç - Project Developer (Ford Otosan AI & ML Academy)
• Nesrin Vatansever - Project Developer (Ford Otosan AI & ML Academy)

License

This project is licensed under the MIT License - see the LICENSE file for details.