Udemy

Platform

English

Language

Data & Analytics

Category

Forecasting Models and Time Series for Business in Python

Learn Holt-Winters, Arima, Sarimax, Tensorflow Time Series, Facebook Prophet, XGBoost for Demand Planning & Forecasting

4.66 (28 reviews)

Students

8 hours

Content

Jul 2021

Last Update
Regular Price

BLUE HOST
Blue Host
Fast, easy, and secure WordPress hosting in minutes + 1 free domain name
$2.95/month

What you will learn

Holt-Winters

TBATS

SARIMAX

Facebook Prophet

Tensorflow Structural Time Series

XGBoost

Time Series Analysis

Demand Planning and Forecasting


Description

Welcome to the most exciting online course about Forecasting Models in Python. I will show 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?

YOU WILL LEARN THE INTUITION BEHIND THE MODELS WITHOUT FOCUSING TOO MUCH ON THE MATH

It is fundamental that you know why a model makes sense and the underlying assumptions behind it. I will explain to you each model using words, graphs, and metaphors, leaving math and the Greek alphabet to a minimum.

THOROUGH COURSE STRUCTURE OF MOST IMPACTFUL ECONOMETRIC TECHNIQUES

The techniques in this course are the ones I believe will be most impactful, up to date, and sought after:

  1. Holt-Winters

  2. TBATS

  3. SARIMAX

  4. TensorFlow Structural Time Series

  5. Facebook Prophet

  6. Facebook Prophet + XGBoost

  7. Ensemble approach

WE CODE TOGETHER LINE BY LINE

I will guide you through every step of the way. I will also explain all parameters and functions that you need to use, step by step.

THE FINAL REASON IS THAT YOU PRACTICE, PRACTICE, PRACTICE.

For each algorithm, there is a challenge. This means that each technique has 2 case studies. The goal is that you apply immediately what you have learned. I give you a dataset and a list of actions you need to take to solve it. I think it is the best way to really cement all the techniques in you.

Did I spike your interest? Join me and learn how to predict the future!


Screenshots

Forecasting Models and Time Series for Business in Python
Forecasting Models and Time Series for Business in Python
Forecasting Models and Time Series for Business in Python
Forecasting Models and Time Series for Business in Python

Content

Introduction

Course Introduction

Link to course material

Course Material

Introduction to Forecasting

Game Plan

Why Forecasting?

Time Series Data and Case Study Briefing

Python - Set Working Directory

Python - Importing Libraries

Python - Loading Data

Python - Forming Data Set

Python - Renaming Dependent Variable

Python - Index Frequency

Python - Visualization

Seasonal Decomposition

Game Plan

Seasonal Decomposition

Prepare Script

Multiplicative and Additive seasonality

Python - Seasonal Decomposition

Error Modelling and Stock Data

Python - Seasonality graphs

Holt-Winters

Game Plan

Training and Test Set

Python - Prepare Script

Python - Training and Test Set

Exponential Smoothing and Holt-Winters

Python - Holt-Winters

Python - Predictions

Python - Visualization

Assessing Time Series Models

Python - MAE and RSME

Python - MAPE function

Python - Exporting Forecasts

Python - Preparing Master Script

Pros, Cons and Challenge

Python - Challenge Solutions

TBATS

Game Plan

TBATS introduction

Python - Prepare Script and Install Package

Autoregressive and Moving Average components

Trigonometric Seasonality and Box Cox

Python - TBATS model

Python - Predictions and Plotting

Python - Accuracy Assessment and Exporting

Pros, Cons and Challenge

Python - Challenge Solutions

ARIMA, SARIMA and SARIMAX

Game Plan

ARIMA and ARMA recap

Python - Prepare Script

Stationarity

Python - Augmented Dickey Fuller Test

Exogenous Variables

Python - Isolating Regressors

Optimizing factors in ARIMA and SARIMA

AIC and BIC

Python - SARIMAX model

Python - Model Summary and Predictions

Python - Visualization, Assessment and Exporting

Pros, Cons and Challenge

Python - Challenge Solutions

TensorFlow Structural Time Series

Game Plan

Structural Time Series

Python - Prepare Script

TensorFlow Structural Time Series

Python - Regressors

Python - Isolate Dependent Variable

Python - Weekly Seasonality

Python - Monthly Seasonality

Python - Trend and Autoregressive Terms

Python - TensorFlow Model

Monte Carlo and Bayes Theorem

Python - Fitting Model

Python - Forecasting

Python - Formatting Predictions

Python - Visualization, Assessment and Exporting

Pros, Cons and Challenge

Python - Challenge Solutions

Facebook Prophet

Game Plan

Facebook Prophet Introduction

Python - Importing Libraries and Data

Python - Transforming Date Variable

Python - Renaming Variables

Dynamic Holidays

Python - holidays

Python - Removing Variable and Training Set

Facebook Prophet Components

Python - Prophet model

Python - Future Dataframe

Python - Forecasting

Python - Visualization

Python - Model Assessment

Cross-Validation

Python - Cross-Validation

Python - Cross-Validation results

Parameters to be tuned

Python - Parameter Grid

Python - Hyperparameter Tuning

Python - Getting Best Parameters

Python - Final Prophet Model

Pros, Cons and Challenge

Python - Challenge Solutions

Facebook Prophet + XGBoost

Game Plan

Prophet + XGBoost step by step

Python - Prepare Script

XGBoost

Python - Extracting Prophet Variables

Python - Training and Test Set

Python - Isolate X and Y

XGBoost Matrices

XGBoost Quirks and Parameters

Python - Setting Parameters

Python - XGBoost Model

Python - Forecasting

Python - Visualization

Python - Assessment and Export

Pros, Cons and Challenge

Python - Challenge Solutions

Ensemble

Game Plan

Why Ensemble?

Python - Prepare Script

Python - Loading Predictions

Python - Ensemble Forecast

Python - Visualization and Assessment

Pros and Cons


Reviews

M
Mike4 July 2021

Very good course, thorough, hands on and well explained. Diago has done a good job explaining all the concepts well.

R
Ruben17 June 2021

Did not talk about making the seris stationary, did not talked about tuning the parameters which I consider important

W
Wagner16 June 2021

Amazing course, excellent teaching. The instructor has mastery of the subject and pass it easily. Congratulations!

F
Filip12 June 2021

Knowledgeable instructor + great content that is easy to follow. And last but not least - the methodology of teaching is excellent.

A
Abhimanyu10 June 2021

I have taken couple of courses by this instructor - Econometrics, and Time series (this course). It is amazing and refreshing to see how he manages to convey the essence of the topic and its practical implementation in programming, without making the lectures too long. And I have liked that he is always quick to resolve queries and doubts on lectures. Continue the good work!! You make learning interesting.

B
Brian10 June 2021

The course was filled with various forecasting models and showed how to use them! The only suggestion would be to add more depth on the parameters/features that a forecaster might focus on to tweak the model. Fortunately, he dives into that - just wanted a bit more depth. This course was amazing! Thank you!

J
Julian2 June 2021

Yet another course where Diogo manages to capture an extremely relevant topic in just the right way. Easy to follow and highly recommended for anyone interested in the topic

E
Edwin18 May 2021

Exceed my expectations! The topics are challenging but the teacher created an atmosphere where difficult concepts are being explained thoroughly using the laymen's language.


4013524

Udemy ID

4/28/2021

Course created date

5/31/2021

Course Indexed date
Bot
Course Submitted by