Introduction-to-Time-Series-Forecasting

In depth introduction to time series forecasting covering a broad range of models. This notebook provides an example of time series analysis on NASDAQ daily closing prices. It includes data loading, visualization, handling missing values, decomposition, hyperparameter tuning for different moving averages, ARIMA modeling, and various statistical diagnostic tests.

Table of Contents

1. Installation
2. Data Loading
3. Data Visualization
4. Handling Missing Values
5. Time Series Decomposition
6. Moving Averages
7. Autocorrelation and Partial Autocorrelation
8. Stationarity Tests
9. ARIMA Modeling
10. Model Diagnostics
11. Contributing
12. Contact Information

Installation

!pip install openbb pandas numpy matplotlib statsmodels scikit-learn

Data Loading

from openbb_terminal.sdk import openbb
df_daily = openbb.stocks.load(symbol = 'ndaq')

Data Visualization

Plots for NASDAQ daily closing prices, trend, seasonal, and residual components.

Handling Missing Values

Code to identify and handle missing values in the dataset.

Time Series Decomposition

Decomposing the time series into observed, trend, seasonal, and residual components.

Moving Averages

Implementation and evaluation of Simple Moving Average (SMA) and Exponential Weighted Moving Average (EWMA) with hyperparameter tuning.

Autocorrelation and Partial Autocorrelation

Visualizing and interpreting the autocorrelation and partial autocorrelation functions.

Stationarity Tests

Includes Dickey-Fuller tests and differencing to achieve stationarity.

ARIMA Modeling

ARIMA modeling includes the process of identifying the best-fitting ARIMA model for the time series and making predictions.

Model Diagnostics

Residual analysis including ACF and PACF of residuals and squared residuals, Ljung-Box test, Kolmogorov-Smirnov test. Includes Goldfeld-Quandt test to identify any heteroskedasticity in the residuals.

Contributing

We welcome contributions to this project. To contribute:

1. Fork the project.
2. Create your feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Add some AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).
5. Open a Pull Request.

Contact Information

For any questions or inquiries, please contact [email protected] - Subject: Github Repo Q, Introduction-to-Time-Series-Forecasting. For a full article walkthrough please visit > https://www.pyfi.com/blog/Introduction-to-Time-Series-Forecasting < and learn more about PyFi's award winning Python for Finance courses which have been trusted by the top financial institutions in the United States and Canada multiple years running here >> https://www.pyfi.com <<