The Machine‐Learning Approach
Abhishek Kumar Mishra · 2020
This chapter presents a hypothetical scenario in which a rule-based system is devised to process credit card applications. It examines the limitations of the rule-based system and a machine-learning system. The chapter discusses the steps involved in building a typical machine-learning solution. Unlike a rule-based solution, he/she cannot create a machine-learning solution without historical data from previous applicants. It is important to have data that is accurate and relevant to the problem they are trying to solve. Most cloud-based data analysis tools allow to upload CSV files, and some also support importing data from cloud-based relational databases. Before building a machine-learning model, separate training and testing datasets need to be created. The training set is used to build the model, whereas the test set is used to evaluate the performance of the model.