Demand Forecasting R Project

Overview

Welcome to the Demand Forecasting project! This project was completed as part of the Coursera Guided Project with instructor Moses Gummadi. The goal of this project was to explore demand forecasting using R, analyze trends, seasonality, and create ARIMA models to predict future demand. This README provides an overview of the project and its structure.

Project Structure

Scenario

This project is organized into various sections, each addressing a specific task in the demand forecasting process. Here's a brief overview of what each section covers:

1. Task 1 - Import Data, Create Time Series Objects

   • Import demand data.
   • Format the date and create additional columns.
   • Summarize demand by week and month.
   • Create time series objects from the demand data.

2. Task 2 - Analyze Demand Trend and Seasonality

   • Analyze the demand trend and seasonality using ACF (Auto-correlation Function) and PACF (Partial Auto-correlation Function).
   • Decompose the data into its components and extract them.
   • Practice analyzing quarterly trend and seasonality for a specific product.

3. Task 3 - Auto ARIMA Modeling and Parameters

   • Explore ARIMA (AutoRegressive Integrated Moving Average) modeling.
   • Use AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion) to select the best model parameters.
   • List and store models, and check if they meet the criteria.

4. Task 4 - Create and Evaluate ARIMA Demand Model

   • Create ARIMA demand models.
   • Check residuals for normality and match periodicity in the data.

5. Task 5 - Forecast Demand, Plot, Extract, and Evaluate

   • Generate forecasts and plot them.
   • Diagnose forecast accuracy and write the forecast output to a CSV file.

6. Capstone Task - 52 Week Forecast for Garden Equipment

   • Perform a 52-week forecast for Garden Equipment.

How to Use

To explore and use this project, follow these steps:

1. Open this project in R Studio.

2. Run the R script for each task by typing it in the Console window or selecting the code and hitting "Run" in the top-left pane.

3. Review the comments within the code to understand the purpose and functionality of each section.

4. Experiment with the code and data to gain hands-on experience in demand forecasting.

Acknowledgments

Special thanks to instructor Moses Gummadi for providing the guidance and expertise needed for this project.

Feel free to reach out if you have any questions or need further assistance. Happy forecasting!

Completion certificate

---

End of Demand Forecasting R Project