A deep understanding of the user's needs, motivations, and pain points is at the heart of any successful business. Using a user-centered approach, you can create experiences that truly resonate with your audience and deliver value.

Entity resolution (ER) determines whether multiple labels are one real-world object and can be referred to as the same or different objects. In this chapter, we will take you through a simulation to determine the genuine users and the proper steps in identifying them.

Let’s start with the simulation case as we work in the high pace fintech industry. Suppose we want to maximize our budget by knowing how many “real people” we can give promos. But you are confused; how do we know this “real person,” and what are the proper steps to start?

After cleaning our data in previous chapter, in this chapter and next chapter we will get our hand dirty and solve Entity Resolution (ER) in practice. Warning! this chapter will require you to have some experience in intermediate python programming language and intermediate sql query.

After collecting all of the essential data for Entity Resolution, you may come across a range of emails, phone numbers, and addresses. The common method involves utilizing an Entity Relationship Diagram to establish connections through paired matching. This approach necessitates several matching attributes to achieve a high match score. However, when handling data with numerous many-to-many relationships between entities and related entities, making connections can grow increasingly complicated.