English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 2h 03m | 246 MB
Use Bayesian analysis and Python to solve data analysis and predictive analytics problems
Bayesian methods have grown recently because of their success in solving hard data analytics problems. They are rapidly becoming a must-have in every data scientists toolkit. The course uses a hands-on method to teach you how to use Bayesian methods to solve data analytics problems in the real world. You will understand the principles of estimation, inference, and hypothesis testing using the Bayesian framework. You will also learn to use them to solve problems such as A/B testing, understanding consumer habits, risk evaluation, adjusting machine learning predictions, reliability analysis, detecting the influence of one variable over an outcome, and many others.
By taking this course, you will be able to apply and use Bayesian methods as part of your data analytics toolbox, thus helping you use Python to solve a majority of common statistical problems in data science.
The course follows a hands-on approach; explanations of core concepts are intuitive and always related to applications. Interesting real-world examples are presented and solved using computational methods, especially the PyMC3 library. Mathematics are used only when necessary.
- Solve interesting statistical and data analytics problems using Python and the Bayesian approach.
- Use the PyMC3 library for data analysis and modeling.
- Core concepts and approaches to using Bayesian Statistics.
- Utilize the Bayesian Theorem to use evidence to update your beliefs about uncertain events.
- Solve problems arising in many quantitative fields using Bayesian inference and hypothesis testing.
- Improve the performance and interpretation of the results of predictive models by using Bayesian methods.