Learn How to Make Machine Learning Work (webinars every Tue in October, Live or on-demand)
To fully use machine learning, we first need to understand both the potential benefits and the techniques to create data-driven models. In this webinar series, we will show you how to easily and automatically apply complex algorithms to data in real world applications.
LIVE OR ON-DEMAND
- LIVE: Tuesdays, October 3, 10, 17, 24, 31st, 10AM – 11AM PDT, 1PM EDT
- ON-DEMAND: If times are inconvenient, please register and we will send you the recordings
- Duration: 45 minutes followed by Q&A
- Cost: Complimentary
Machine learning may sound like an overwhelmingly complicated concept rather than a data-driven method to extract insights that drive future business decisions. To fully utilize machine learning, we first need to understand the benefits to our organization, and the techniques to create models based on questions we need to answer. In this webinar series, we will show you how to easily and automatically apply complex algorithms to data in real world applications.
SESSIONS: (Each webinar is stand-alone)
- Data Science: Proven Value in a Variety of Industries (OCTOBER 3)
- Improve your Classification Models with Key Machine Learning Methods (CART Decision Trees, Gradient Boosting, Random Forests) (OCTOBER 10)
- Improve your Regression Models with key Machine Learning methods (MARS non-linear regression, Gradient Boosting, Random Forests) (OCTOBER 17)
- Real-world demonstration for the beginner modeler (OCTOBER 24)
- Real-world demonstration for advanced modelers (OCTOBER 31)
Who should attend:
- Beginners will learn the basics. Data Science techniques that encompass the foundation of data modeling— key methods, building a predictive model, extracting value from complex datasets.
- Advanced Modelers will continue to evolve their ability to leverage the power of data science. Improve both regression and classification models by utilizing automated features that shorten the time to create an accurate model. We also cover how to better handle missing data, outliers, significant interrelationships among variables that are otherwise hard to capture.