What you will learn

  • Impute missing values

    When historical records don't exist, use episodic time series analysis to fill in the gaps in your data.

  • Perform what-if analysis

    Adapt your forecasting model to create a range of different what-if scenarios with the synthetic control method.

  • Infuse machine learning

    Leverage ML algorithms, including neural networks, for time series classification, to categorize your data or spot outliers.

Time Series Forecasting

Example: Demand Forecasting (Retail, E-Commerce)

Leverage historical sales data to predict future consumer demand and trends. Become proficient in various models, such as ARIMA or exponential smoothing, to confidentially select the best one for your business case.

Operations Planning

Example: Supply Planning (Manufacturing)

Use historical time series data to gain insights into operational inputs, and better understand the impact of changes in these inputs.

Time Series Classification

Example: Fraud Detection (Banking)

Historical patterns can help you predict the future behavior of your system, classify the inputs into categories and detect any anomalies in the data.

Course Outline

    1. Welcome to the course!

    2. How this course is organized

    3. How to get support

    4. Glossary

    1. Why time series analysis?

    2. Application of Time Series Analysis

    3. Representation of time series data

    4. Quiz: Time Series Basics

    1. About the module

    2. Imputation of missing data

    3. Forecasting - Auto Regressive Model

    4. Quiz: Imputation & Forecasting

    5. Get Template Project

    6. Project: Weekly Walmart Sales

    7. Project 'Walmart': Implementation instruction

    8. Project 'Walmart': Turn in an assignment

    1. About the module

    2. Episodic Time Series

    3. Forecasting with Episodic Time Series

    4. What-if Analysis

    5. Imputation with Episodic Time Series

    6. Quiz: Episodic Time Series

    7. Project: Cricket Runs

    8. Project 'Cricket Runs': Implementation instruction

    9. Project 'Cricket Runs': Turn in an assignment

    1. About the module

    2. Why time series classification?

    3. Time Series Classification Methods

    4. Brief introduction to neural networks

    5. Quiz - Time Series Classification

    6. Project: Accelerometer

    7. Project 'Accelerometer': Implementation instruction

    8. Project 'Accelerometer': Turn in an assignment

    1. Course Feedback

    2. Conclusion

Course details

  • 35 lessons
  • 2 hours of video
  • 3 projects
  • Certificate

Start this course today,

add no-code AI skills to your resume tomorrow