Data Forecasting and Segmentation Using Microsoft Excel

Perform time series forecasts, linear prediction, and data segmentation with no-code Excel machine learning

Purchase of the print or Kindle book includes a free PDF eBook

What’s inside

• Techniques to segment data, perform regression predictions, and time series forecasts without writing any code
• A guide to grouping multiple variables with K-means using Excel plugin without programming
• Easy-to-follow instructions on building, validating, and predicting with a multiple linear regression model and time series forecasts

You’ll get the most out of this book if

• You're a data analyst, a business analyst, or a data science professional
• You work in MIS, finance, or auditing and have a solid grasp on MS Excel

What your journey will look like

This book guides you through basic statistics to test whether your data can be used to perform regression predictions and time series forecasts. The exercises use real-life data from Kaggle, such as demand for seasonal air tickets and credit card fraud detection.

You'll learn how to apply the grouping K-means algorithm to find segments of your data that are impossible to see with other analyses. By analyzing groups returned by K-means, you'll be able to detect outliers that could indicate possible fraud or a bad function in network packets.

By the end, you'll be able to use the classification algorithm to group data with different variable and train linear and time series models to perform predictions and forecasts based on past data.

Some of the things you’ll learn from this book

• The importance of machine learning for classifying data segmentation
• How to perform basic statistics tests for regression variable dependency
• Test time series autocorrelation to build a useful forecast
• Using Excel add-ins to run K-means without programming
• Segment outlier analysis for possible data anomalies and fraud
• Building, training, and validating multiple regression models and time series forecasts

Table of Contents

1. Understanding Data Segmentation
2. Applying Linear Regression
3. What is Time Series?
4. An Introduction to Data Grouping
5. Finding the Optimal Number of Single Variable Groups
6. Finding the Optimal Number of Multi-Variable Groups
7. Analyzing Outliers for Data Anomalies
8. Finding the Relationship between Variables
9. Building, Training, and Validating a Linear Model
10. Building, Training, and Validating a Multiple Regression Model
11. Testing Data for Time Series Compliance
12. Working with Time Series Using the Centered Moving Average and a Trending Component
13. Training, Validating, and Running the Model

Fernando Roque has 24 years of experience working with statistics for quality control and financial risk assessment of projects since planning, budgeting, and execution. Fernando works applying python k-means and time-series machine-learning algorithms using vegetable activity (NDVI) drones’ images to find the crop´s region with more resilience to droughts. He also applies time-series and k-means for supply chain management (logistics) and inventory planning for seasonal demand.