Introduction to time series forecasting
Description
This course aims to explore the fundamentals and key concepts of the time series analysis ranging from conventional statistical to deep-learning-based approaches.
Outline
Notation and basics for time series
Basics of regression and forecasting
Fundamentals
Autoregressive models
ARIMA
SARIMA
Neural-network-based approaches for forecasting:
MLP
CNN
LSTM
RNN
Recommended textbooks
[1] Brownlee, Jason, Deep learning for time series forecasting: predict the future with MLPs, CNNs and LSTMs in Python, 2018, Machine Learning Mastery. https://machinelearningmastery.com/deep-learning-for-time-series-forecasting/
[2] Peter J. Brockwell and Richard A. Davis. Introduction to time series and forecasting, 2nd ed. p. cm. Springer https://link.springer.com/book/10.1007/b97391
[3] Box, George E. P. Time series analysis : forecasting and control. Fifth edition / George E.P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung. https://onlinelibrary.wiley.com/series/1345
[4] David M. Levine, David F. Stephan, Kathryn A. Szabat, Statistics for Managers Using Microsoft Excel, 9th edition, Published by Pearson https://www.pearson.com/store/p/statistics-for-managers-using-microsoft-excel/
[5] Pena, Daniel, George C. Tiao, and Ruey S. Tsay. A course in time series analysis. John Wiley & Sons, 2011. https://www.wiley.com/en-us/A+Course+in+Time+Series+Analysis-p-9780471361640
Resources
General course instructions and guidelines
Lectures
Lecture 0: Motivation and course presentation
Lecture 1: Basics of times series
Resources for the lecture:
Linear regression (Python Data Science Handbook Notebook (HTML))
Lecture 2: Introduction to deep learning for time series forecasting
Lecture 3: Introduction to Recurrent Neural Networks (RNNs)
Lecture 4: Long Short Term Memory (LSTM)
Lecture 5: Convolutional Neural Networks (CNN) for Time Series
Lecture 6: Summary and final remarks
(Extra) Lecture: Summary
Another example: Sport Car Price Prediction using Decision Tree Regressor, AdaBoost Regressor, and Random Forest Regressor
Resources:
Comparison of benchmark forecasting techniques (Python - HTML)
Skforecast: time series forecasting with Python, Machine Learning and Scikit-learn (link)
𝐏𝐲𝐂𝐚𝐫𝐞𝐭 - 𝐍𝐞𝐰 𝐓𝐢𝐦𝐞 𝐒𝐞𝐫𝐢𝐞𝐬 𝐌𝐨𝐝𝐮𝐥𝐞 (𝐁𝐞𝐭𝐚)
Performance evaluation toolbox for time series models (Git)
How to Use XGBoost for Time Series Forecasting (Link)
tsflex (Git): flexible time-series operations - Python toolkit for processing & feature extraction, making few assumptions about input data.
Course:Time Series Analytics and Forecasting by Lorenzo Nespoli (Link).
Initializing neural networks (Link).
Amazon - Chronos:
Example: Algorithms of Air Quality Estimation: A Comparative Study of Stochastic and Heuristic Predictive Models
Mid-term exam
Project ideas:
Assignments
Part I: Basics of time series
Part II: Long Short Term Memory (LSTM)
Dataset: Gold Price
Part III: Introduction to Convolutional Neural Networks (CNNs):
Dataset: Climate