Time-Series Forecasting Using the Prophet Algorithm

Predicting Trends and Patterns with Advanced Forecasting Techniques

Schedule
26 – 28 March 2024
09.00 – 15.00 WIB
Algoritma Training Center
Menara Kadin, 4th Floor, Jl. H. R. Rasuna Said No. Kav. 2-3, South Jakarta – 12950.
Investment
Rp. 5.550.000

Hours Course

WORKSHOP STARTS IN

0Weeks0Days0Hours0Minutes0Seconds

Overview:

Our “Time Series Forecasting with Prophet” course is designed for beginners who want to learn how to analyze and predict time series data in a simple, easy-to-understand way. This course covers two main areas: basic Python for data analysis and the basics of time series forecasting using the Prophet algorithm. We start from the ground up, teaching you the essentials of Python programming and how to manage data using Pandas. You’ll learn about time series data and how to make predictions with Prophet, all explained in a beginner-friendly manner. Our experienced instructors and teaching assistants provide one-on-one tutoring to ensure you understand each concept. By the end of this course, you’ll be able to confidently apply your new forecasting skills to real-world data, making informed decisions with ease.

Course Syllabus

Python Programming Basic

Working with Jupyter Notebook: Gain hands-on experience using the Jupyter Notebook environment, a popular tool for interactive coding and data analysis.
Python Syntaxes and Jargons: Learn the fundamental syntax and terminology of Python programming to build a solid foundation for data analysis.

Working with Data

Introduction to Dataframe: Understand the concept of a DataFrame, a key data structure in Python for handling and analyzing tabular data.
Reading & Extracting Dataframes: Explore methods to read and extract data from various sources, preparing it for analysis.
Python Data Types: Familiarize yourself with different data types in Python, essential for effective data manipulation.
Exploratory Data Analysis: Learn techniques for exploring and summarizing data to gain insights and identify patterns.

Setting Up Connections and Data Sources

Categorical and Numerical Variables: Understand the distinction between categorical and numerical variables and their significance in data analysis.
Using Panda’s Built-in Statistics summary: Explore Pandas, a powerful library for data manipulation, and learn to generate statistical summaries for better understanding.
Indexing and Subsetting: Master the techniques of indexing and subsetting data to extract relevant information for analysis.

Data Preparation

Data types inspection: Examine data types within the dataset to ensure consistency and compatibility with modeling algorithms.
Data sorting: Implement sorting techniques to organize data for effective analysis and modeling.
Check Missing Value: Learn methods to identify and handle missing values in time series data.
Feature Selection: Understand the process of selecting relevant features for modeling to improve forecasting accuracy.

Exploratory Data Time Series

Time series frequency: Explore the concept of time series frequency and its implications on data analysis.
Data aggregation: Aggregate time series data to a meaningful level for better understanding and model performance.
General Additive Model (GAM): Introduce the General Additive Model for time series decomposition into trend, seasonality, and residual components.
Decomposition of Time Series Data: Understand the process of decomposing time series data into its constituent parts.
Extracting Trend and Seasonality: Extract and interpret trend and seasonality components in time series data.

Data Pre-Processing

Cross Validation for Time Series Data: Implement cross-validation techniques tailored for time series data to assess model performance.
Train-Test Split: Learn how to split time series data into training and testing sets while maintaining temporal order.

Model Time Series (‘prophet’)

Baseline Model Preparation: Set up a baseline time series forecasting model using the Prophet algorithm.
Baseline Model Adjustment: Fine-tune the baseline model by adjusting its components, including trend and seasonality.
Trend Adjustment: Explore methods to adjust and optimize the trend component of the time series model.
Seasonality Adjustment: Customize and optimize seasonality in the time series model.
Fourier order for seasonality component: Understand the use of Fourier order to control the flexibility of seasonality modeling.
Modeling holidays and special events: Incorporate holidays and special events into the model for enhanced accuracy.
Built-in country holidays: Leverage built-in country-specific holidays for improved model performance.
Hyperparameter Tuning: Optimize model hyperparameters for better forecasting results.

Performance Evaluation

Evaluation metrics: Understand and apply various evaluation metrics to assess the performance of time series forecasting models.
Error: Explore different error metrics to quantify the accuracy and reliability of the forecasting model.

Model Implementation

Model Forecasting: Implement the trained time series forecasting model to make predictions on new data, enabling practical application of the acquired skills.

Course Receivables:

Lecturer’s Notes
Including Course Books (PDF), HTML files, course transcripts (if any).
Highly-accelerated Learning
Learn under the assistance of mentorship of our lead instructor and a band of qualified teaching assistants throughout each course.
Certification of Completion
Show current employer hat you’ve completed the course with a signed certificate of completion.
Quality Learning Environment
We pay meticulous attention to the logistical details of our workshops: quality audio and visual setups, comfortable sitting arrangements, and small group size.
Refreshments & Coffee Break
In our commitment to delivering a premium experience, we collaborate with leading catering services in Jakarta. Our aim is to ensure that all participants are served delectable lunches and revitalizing coffee breaks.

ABOUT THIS SERIES

Courses in this series cater to a diverse audience: from casual learners and working professionals to those venturing into data science and machine learning without a programming background.

We recognize that many students may not have prior expertise in statistics, mathematics, or algebra. Therefore, our courses are designed with a gentle learning curve, placing a strong emphasis on hands-on experience and individualized instruction. Our dedicated team of instructors and teaching assistants ensure personalized guidance every step of the way.

Teaching Methodology:

Students work through tons of real-life examples using sample datasets donated by our mentors and corporate partners. We believe in a learn-by-building approach, and we employ instructors who are uncompromisingly passionate about your growth and education.

Get In Touch

PT. Algoritma Data Indonesia.
Menara Kadin, 4th Floor. Kuningan, DKI Jakarta 12950.
WhatsApp: 0816-692-471
Email: community@algorit.ma

Data Science School

For Corporates
For Individuals
Alumni
Testimonials

Company

About us
Contact us
Join Us
Blog
Press