What's Next?

Thank you for taking this course. We hope you’ve learned much throughout this course and now feel capable of crafting valuable machine learning models.

Honing your skills

Like any other technical skill, machine learning requires hands-on practice for proficiency. The best way to get this hands-on experience is through projects. There are three primary sources of applied machine learning projects.

The first source of projects can be your current job. This is the best source of projects for your machine learning journey. Whether or not you have an official data title (e.g., data scientist), you can often find business problems that can be potentially addressed using machine learning. Seek out these types of problems and offer to help.

The second source of projects comes from you finding publicly available datasets and then crafting machine learning models that make useful predictions for those datasets. Examples of where you can find data for your projects include governmental agencies and the University of California, Irvine Machine Learning Repository (UCI ML Repository).

The third source of projects is the Kaggle website. Kaggle is an online platform and community that hosts machine learning competitions. Kaggle also offers many datasets outside of competitions that you can use to build your skills.

Expanding to new business problems

This course has focused on supervised learning, the most common form of machine learning used by professional data scientists. After developing your skills with supervised learning, expanding your skillset into new types of business problems is encouraged.

Unsupervised learning, especially cluster analysis, should be the next stop on your machine learning journey. Professional data scientists commonly use cluster analysis to discover new patterns in unlabeled data. There are many practical use cases for cluster analysis, including clustering documents and customer segmentation.