Integrating GenAI into “Thinking Like a Data Scientist” Methodology – Part II

My journey continues as I integrate a GenAI tool (Bing AI) with my Thinking Like a Data Scientist (TLADS) methodology. In part 1 of this series, I used Bing AI to validate, augment, and enhance the first three steps in the TLADS methodology (Figure 1):

• TLADS Step #1: identify and assess the targeted business initiative, including its desired outcomes, benefits, impediments, risks, and the KPIs and metrics against which I would measure outcomes’ effectiveness and benefits and monitor impediments and risks.
• TLADS Step #2: identify the key initiative stakeholders, understand the business initiative’s importance to them, key supporting decisions, and the KPIs and metrics against which they will measure the success of that business initiative.
• TLADS Step #3: identify and understand the business initiative’s key business entities around which I want to build analytic profiles to support my business initiative.

And the results yielded a much deeper understanding of the business initiative – and its key components – that we were trying to address with data and analytics.

Now, we want to use the results of these first three steps to create the prompt narrative that will help us:

• TLADS Step #4: Identify and triage the use cases that support the targeted business initiative.
• TLADS Step #5: Identify potential Analytic Scores and their associated Features for our prioritized use case.

Figure 1: Thinking Like a Data Scientist Methodology – Updated Version 3.0

TLADS Step #4a: Identify and Assess Potential Use Cases

We can use Bing to blend stakeholders’ desired outcomes, key decisions, and KPIs from Steps 1 and 2 of TLADS to identify potential use cases. Using prompts, we can validate the use cases that make up the modified Use Case Identification and Assessment canvas (Figure 2).

Figure 2: Use Case Identification and Assessment Canvas

Here are some prompts that we can use to identify, validate, and expand our understanding of the potential use cases that support our targeted business initiative:

• Bing Prompt: Looking across an aggregated view of our stakeholders’ requirements, what are the top 10 – 15 potential use cases that support our targeted business initiative?
• Bing Request: Can you identify for each use case the key decisions for each use case, the desired outcomes for that use case, and the KPIs and metrics against which to measure use case key decisions and outcomes’ effectiveness?
• Bing Request: What other use cases should I consider supporting our targeted business initiative?
• Bing Request: What is your rationale for why I should consider these other use cases?
• Bing Request: Which of these use cases is most important or impactful for our targeted business initiative?
• Bing Request: What is your rationale for determining that these use cases are the most important use cases given the targeted business initiative?
• Bing Request: What factors did you use to determine use case importance, and why did you pick those factors?

Identifying, validating, assessing, and triaging the potential use cases sets up the next step of the TLADS methodology – the all-important use case prioritization process.

TLADS Step #4b: Prioritize Use Cases

Now we get to the part of the TLADS process where we want to bring together the different stakeholders to prioritize the use cases based on “value” and “implementation feasibility.” Gathering and assessing each stakeholder’s perspective and requirements (desired outcomes, key decisions, and the KPIs and metrics against which to measure business initiative effectiveness) is critical before engaging in this interactive, sometimes controversial engagement (Figure 3).

Figure 3: Prioritization Matrix

CRITICAL NOTE: While the GenAI product can provide a representative view of the stakeholder’s perspectives and requirements, GenAI will NEVER replace the need to conduct interviews to gather those perspectives and requirements directly from your subject matter experts and key stakeholders. NEVER! To gain cross-stakeholder alignment and consensus on which use case to prioritize, you MUST ensure that everyone has a voice in that prioritization process.

Here are some prompts that we can use to understand the relative value and implementation feasibility of the use cases in light of our targeted business initiative:

• Bing Request: Create a matrix that scores the likely impact of each use case on a scale of 1 to 100 to support the desired outcomes and the KPIs and metrics against which to measure outcomes’ effectiveness in supporting the targeted business initiative.
• Bing Request: What is the rationale for the value scores that you gave each use case?
• Bing Request: Create a matrix that assesses or scores on a scale of 1 to 100 the implementation success likelihood of each use case from an implementation feasibility perspective using the potential impediments identified for the targeted business initiative.
• Bing Request: What is the rationale for the implementation feasibility scores that you gave each use case?
• Bing Request: Create a 2×2 matrix plotting each use case on the matrix where the vertical dimension of the matrix is the value score and the horizontal dimension of the matrix is the implementation feasibility score.

I was impressed by Bing’s ability to create value and implementation feasibility scores and then convert those scores into a 2×2 prioritization matrix, though I’ll have to create the actual quadrant matrix using Excel myself (Table 1).

Table 1: Creating and Mapping Value and Implementation Feasibility Scores

The value and implementation feasibility scores created by Bing provide a starting point for the value and implementation feasibility scores you will create based on your user interviews. You could even enter the interview notes into the GenAI tool to uncover additional value and implementation feasibility factors that may not have jumped out of the individual interviews.

As always, you will have to employ critical thinking, your experience, the expertise of your subject matter experts, and that soft human touch to drive the group exercise to assess each use case’s relative value and implementation feasibility in light of the targeted business initiative.

TLADS Step #5: Identify Potential Scores and Associated Features

This was one area where Bing dramatically transformed the TLADS methodology! Given all the information that I had fed into Bing about the targeted business initiative (objectives, KPIs / Metrics, benefits, impediments, risks), our key stakeholders (desired outcomes, key decisions, KPIs and metrics), the key business entities (desired entity insights), and our potential use cases, I guided Bing to give me a list of potential analytic scores and associated features for our targeted each use case.

Note: at this point in the TLADS methodology, we have identified and gotten cross-stakeholder consensus on our prioritized use case. Consequently, this example will focus on the use case of “Improving Local Events Marketing Effectiveness.”

Figure 4: Brainstorm Analytic Scores and Features

Here are some prompts that we can use to identify potential analytic scores and supporting features to help optimize the key decisions that comprise our prioritized use case:

• Bing Prompt: For the use case “Improve Local Events Marketing Effectiveness,” identify 1 to 2 analytics scores that I might want to create to help me optimize those local events decisions.
• Bing Prompt: What features should I consider when creating the respective analytic scores?
• Bing Prompt: What Business Entities are impacted by the “Improve Local Events Marketing Effectiveness” use case?
• Bing Prompt: How does the prioritized use case impact these Business Entities?
• Bing Request: Create a matrix that maps the analytic scores and features to the business entities to Decision #1: decide in which local events to promote.

Here is the Bing Response for the last prompt (Table 2).

For Decision #1: decide on which local events to promote:

Table 2: Map Business Entity to Analytic Score and Features for Key Use Case Decision

The ability of Bing to create these cross-tab tables is impressive. I’m still trying to determine how to exploit this Bing capability further.

Summary: Integrating GenAI + TLADS – Part 2

GenAI has certainly expanded the quality and creativity of the TLADS process for Steps 4 and 5:

• TLADS Step #4: Identify and triage the use cases that support the targeted business initiative.
• TLADS Step #5: Identify potential Analytic Scores and their associated Features for our prioritized use case.

The next part of this series on Integrating a GenAI tool with my Thinking Like a Data Scientist methodology will focus on the following:

• TLADS Step #6: Explore the Analytic Algorithms we might use to build the analytic scores. This is an entirely new step of the TLADS process, totally enabled by the GenAI tool. And the learnings from the addition of this step are stunning.
• TLADS Step #7: Map Scores to Recommendations, where we link the analytic scores to the recommendations that will drive the precision decisions that seek to optimize our prioritized use case.
• TLADS Step #8: User Interface and Feedback. Actually, I don’t even know what to expect by trying to integrate the GenAI tool with this step because I haven’t even gotten to it yet. Yea, real-time learning.

One big takeaway from this experiment so far is that my most significant advancements haven’t been regarding productivity but have been in innovation. Yes, I can do some things faster (which is nice). Still, my biggest win is the ability to unleash my natural curiosity to explore different prompts and expand the TLADS conversation. I frequently circle back in the methodology because I have thought of another idea I want to explore with Bing AI.

And while not all my prompts pan out (I have a separate document full of failed prompts), every prompt gives new insights into how to articulate the next prompt better. Yes, the exercise has been enlightening and damn fun!