Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Language
English
Taught by
Diogo Alves de Resende
Rating
Course Overview
Time Series with Deep Learning (LSTM, TFT, N-BEATS), GenAI (Amazon Chronos), Prophet, Silverkite, ARIMA. Demand Forecast
Updates September 2025:
All the Darts library sections were re-recorded.
New sections on Intermittent Time Series and Classification for Time Series.
New Projects!
More Concise videos by coding with GenAI.
Updates August 2025:
New AI Course Assistant is live!
Updates July 2025:
Fully updated the exercises in the section Python Essentials.
Updates March 2025:
Google TSMixer Launched
Introduction to Time Series Analysis and Exponential Smoothing Python tutorials remade.
Updates December 2024:
Amazon AutoGluon launched
Library requirements.txt file for all sections added
Updates October 2024:
Amazon Chronos launched
N-BEATS launched
Updates September 2024:
TFT and TFT Capstone Project added
Updates August 2024:
Course remade 100%
Silverkite, LSTM and Projects added
Welcome to the most exciting online course about Forecasting Models in Python.
I will show you everything you need to know to understand the now and predict the future.
Forecasting is always sexy.
Knowing what will happen usually drops jaws and earns admiration.
On top, it is fundamental in the business world. Companies always provide Revenue growth and EBIT estimates, which are based on forecasts.
Who is doing them?
Well, that could be you!
WHY SHOULD YOU ENROLL IN THIS COURSE?
Master the Intuition Behind Forecasting Models
No need to get bogged down in complex math.
This course emphasizes understanding the why behind each model. We simplify concepts with clear explanations, intuitive visuals, and real-world examples—focusing on what really matters so you can apply these techniques confidently.
Comprehensive Coverage of Cutting-Edge Techniques
You’ll dive deep into the most advanced and sought-after time series forecasting methods that are crucial in today’s data-driven world:
Exponential Smoothing & Holt-Winters – Handle trends and seasonality with elegance.
Advanced ARIMA Models (SARIMA & SARIMAX) – Incorporate external variables for enhanced forecasts.
Facebook Prophet – Robust, high-accuracy forecasts with minimal data prep.
Temporal Fusion Transformers (TFT) – State-of-the-art deep learning for multiple time series.
LinkedIn Silverkite – Flexible, powerful forecasting across contexts.
N-BEATS – Cutting-edge neural networks for diverse forecasting challenges.
GenAI with Amazon Chronos – Discover how generative AI is revolutionizing forecasting.
Google TSMixer (NEW) – Leverage Google’s breakthrough architecture for time series.
Amazon AutoGluon (NEW) – Automate high-performance forecasting pipelines.
Intermittent Time Series (NEW) – Tackle irregular, sporadic patterns with specialized techniques.
Classification for Time Series (NEW) – Expand beyond forecasting into predictive categorization.
Code Python Together, Line by Line
We’ll code side by side, ensuring you understand every step.
From data preparation to model implementation, you’ll learn how to write and refine each line of Python code needed to master these forecasting techniques.
Practice, Practice, Practice
Each lesson includes hands-on challenges and case studies, from sales to demand forecasting
You’ll apply what you’ve learned to real datasets, solve real-world problems, and solidify your skills through practical application.
Are You Ready to Predict the Future?
Did I spike your interest? Join me and learn how to predict the future!
Course Content
- 38 section(s)
- 396 lecture(s)
- Section 1 Time Series Analysis and Forecasting with Python
- Section 2 PART 1 - TIME SERIES ANALYSIS
- Section 3 Python for Time Series Analysis
- Section 4 Introduction to Time Series Forecasting
- Section 5 Time Series Analysis Practice
- Section 6 Exponential Smoothing & Holt-Winters
- Section 7 HOLT-WINTERS CAPSTONE PROJECT: Air miles
- Section 8 ARIMA, SARIMA and SARIMAX
- Section 9 PART 2: MODERN TIME SERIES FORECASTING
- Section 10 (Facebook) Prophet
- Section 11 CAPTONE PROJECT: Prophet
- Section 12 Intermittent Time Series
- Section 13 Mid-course Feedback
- Section 14 PART 3 - DEEP LEARNING FOR TIME SERIES FORECASTING
- Section 15 RNN - LSTM
- Section 16 LSTM - Multiple Time Series Forecasting
- Section 17 Temporal Fusion Transformers (TFT)
- Section 18 CAPSTONE PROJECT: Multiple Series with TFT
- Section 19 N-BEATS
- Section 20 PART 4 - ADVANCED CONTENT FOR TIME SERIES FORECASTING
- Section 21 GenAI for Time Series: Amazon Chronos
- Section 22 Amazon AutoGluon
- Section 23 Google TSMixer
- Section 24 Classification for Time Series
- Section 25 End of Course Feedback
- Section 26 Time Series Analysis Graveyard
- Section 27 Linkedin Silverkite
- Section 28 CAPSTONE PROJECT: Build an Automated Time Series Forecasting Model
- Section 29 APPENDIX - Python for Data Analysis Course
- Section 30 Python Essentials
- Section 31 Book Review
- Section 32 Variable Types and Operators
- Section 33 If-else and Conditionals
- Section 34 Python Intermediate
- Section 35 CAPSTONE PROJECT: Virtual Escape Game
- Section 36 Pandas
- Section 37 Pandas Challenge
- Section 38 What's Next?
What You’ll Learn
- Understand the fundamental principles of time series data and its significance in forecasting across various industries., Differentiate between various time series forecasting models such as Exponential Smoothing, ARIMA, and Prophet, identifying when to use each model., Apply Exponential Smoothing and Holt-Winters methods to seasonal and trend-based time series data to create accurate forecasts., Implement SARIMA and SARIMAX models in Python, incorporating external variables to enhance the predictive power of your forecasts., Develop time series models using advanced techniques such as Temporal Fusion Transformers (TFT) and N-BEATS to handle complex datasets., Optimize forecasting models by tuning parameters and using ensemble methods to improve accuracy and reliability., Evaluate the performance of different forecasting models using metrics such as MAE, RMSE, and MAPE, ensuring the robustness of your predictions., Code Python scripts to automate the entire time series forecasting process, from data preprocessing to model deployment., Implement deep learning models such as RNN and LSTM to accurately forecast complex time series data, capturing long-term dependencies., Develop and optimize advanced forecasting solutions using Generative AI techniques like Amazon Chronos, incorporating state-of-the-art methods.
Skills covered in this course
Reviews
-
MMatteo Spoladore
The course is too approximate and overly simplistic, and most of the concepts are not properly explained but rather treated as if they should be intuitively understood. For example, every time a choice is made between an additive or multiplicative model, it is done without a statistical test or any explicit analysis of variance. In addition, many sections appear to be generated by ChatGPT. In the AI era this may be considered normal, but such an approach should only be used to speed up certain parts of the work, not to skip fundamental analytical steps without providing a specific theoretical explanation. Otherwise, students become unable to understand what an LLM suggests, why it suggests it, and how to improve upon it. In summary, it is a course that is too simple and insufficiently detailed. It is not suitable for beginners because it does not allow them to build a solid foundation to conduct meaningful analyses of the topics covered.
-
MManoj kumar yendluri
As coming to the explanation of insights and deriving insights, explaining the theory is clumsy and not understandable
-
SSergio Rodriguez
very well explained and illustrated with examples from reality
-
NNeelkanth Mehta
I like that the course covers many modern time series analysis concepts; but the course delivery and structure needs improvement.
