How do you apply optimal stopping to make a community data-driven decision?

Optimal stopping is a decision-making strategy used to determine when to stop searching for better options and make a decision based on the available data. In a community setting, this can help make data-driven decisions that balance the trade-offs between time, effort, and the quality of the outcome. 

Let’s walk through a real-world example: Imagine a community that wants to hire a new park manager. They have received applications from several candidates and will interview each one. The community’s goal is to find the best possible candidate while minimizing the time and effort spent on the interview process. 

Step 1: Determine the stopping point  

First, we need to determine the optimal stopping point. One common rule of thumb is the “37% rule.” According to this rule, we should review 37% of the options, in this case, the applicants, and then select the next candidate that is better than all the previous ones. So if there are 20 applicants, we should interview about 7-8 applicants (37%) before making a decision. 

Step 2: Interview the first 37% of the candidates  

Interview the first 37% of applicants, and keep track of the best candidate among them. This step is essential because it helps us set a benchmark for comparison. 

Step 3: Continue interviewing and apply the optimal stopping rule  

After interviewing the first 37% of applicants, continue interviewing the remaining candidates, but now apply the optimal stopping rule. If you come across a candidate who is better than the best candidate from the initial 37%, hire them and stop the process. 

By applying the optimal stopping rule, you gain the following benefits: 

1. Efficiency: You reduce the time and effort spent interviewing every candidate, which could be exhaustive and time-consuming. 
2. Balance: The optimal stopping rule strikes a balance between gathering enough data (interviewing candidates) and making a timely decision (hiring the best one). 
3. Confidence: Following a data-driven decision-making process can help the community feel more confident in the final choice, knowing that it was based on a sound methodology.

It’s important to note that optimal stopping isn’t a foolproof method and doesn’t guarantee that you’ll always make the best decision. However, it’s a helpful strategy for making data-driven decisions in situations with limited information and resources.