[Zerotomastery] Time Series Forecasting with Python
This project-based course will put you in the role of a Business Data Analyst at Airbnb tasked with predicting demand for Airbnb property bookings in New York. To accomplish this goal, you’ll use the Python programming language to build a powerful tool that utilizes the magic of time series forecasting.
The world is changing. Every decision must be made faster, smarter, and more accurately. And that’s possible with business data analysis. You’ll learn new skills and put them to the test in this project that puts you in the hypothetical scenario of a Business Data Analyst at Airbnb tasked with predicting demand for Airbnb properties in New York. You’ll use Python to build a tool utilizing time series forecasting to help Airbnb make the best, most accurate decision, and have a portfolio project that you can use to impress employers.
What you’ll learn
- How to utilize the power of time series forecasting to predict the future
- How to use the four most relevant forecasting models used by Business Data Analysts today
- Practice the day-to-day skills needed for Business Data Analysis
- Build an impressive project to add to your portfolio to help you get hired
- Enhance your proficiency with Python, one of the most popular programming languages
Let’s start at the beginning: What is Time Series Forecasting?
A time series is where you analyze data in consecutive time periods, such as days, weeks, years, business days, or really any time period. Taking the impact of time into account is key in successful data analysis, and time series help you understand that and use it to your advantage.
Forecasting you’ve probably heard about before. The weatherperson forecasts the weather for you every day. What you’re doing when forecasting is trying to predict the future as accurately as possible.
So time series forecasting is really about using time series data and analysis to forecast what the future is likely to look like.
Sounds pretty useful, right?
Well, just like the weatherperson, you might not be able to perfectly predict the future, but with the right data, tools, and analysis you can make sure your prediction is the best it can be and be able to rely on your predictions with a high degree of trust.
Why Should I Learn By Building A Project?
Building a project is one of the best ways to learn. At ZTM, we’re all about learning by doing. It’ll teach you how to actually work in the real world and not to shy away from the hard stuff.
Plus to land your dream job you’re going to need portfolio projects that you can use to show off your skills to employers. This project will be a great addition to your portfolio that you can use to wow your future employers and land your dream job.
What Will I Learn In This Project?
With this project you’ll learn the four most relevant forecasting models used by Business Data Analysts today including the latest tools needed to utilize them.
But there’s more. Through this project you’ll also learn about:
1. Facebook Prophet: a tool developed by Meta (Facebook) for producing reliable forecasts that assist with planning and setting business goals.
2. SARIMAX Modeling in Python: what is SARIMAX? Well it stands for “Seasonal Auto-Regressive Integrated Moving Average with eXogenous” factors, which we know is a mouthful (thank goodness for acronyms!). All you need to know for now is that SARIMAX is a great tool for time series analysis and is part of the ARIMA family of models.
3. LinkedIn Silverkite: LinkedIn has developed a top forecasting model as well, called Silverkite! This is arguably even better than Facebook Prophet, though each have their uses. It uses automated modeling to make forecasts better and more accurate.
4. Recurrent Neural Networks: learn and utilize cutting-edge neural networks as they are applied to time series, including Long Short-Term Memory, a deep learning forecasting model that is highly marketable and sought-after!
5. The Ensemble Methodology: a common forecasting methodology that combines forecasts from multiple models to improve accuracy.
One of the best parts of this project (and all ZTM courses) is that you won’t be learning alone.
By enrolling today, you’ll also get to join our exclusive live online community classroom to learn alongside thousands of students, alumni, mentors, TAs and Instructors.
How well can you use time series forecasting to predict the future? Click Start Learning Now to join the Academy and start building this portfolio project to find out. We’ll see you inside!
Taught by: Diogo Resende
Last updated: April 2023
Size: 1.56 GB