DIY With AI: The Home Depot's Huiming Qu
26:48 Share

Today, we're airing an episode produced by our friends at the Modern CTO Podcast, who were kind enough to have me on recently as a guest. We talked about the rise of generative AI, what it means to be successful with technology, and some considerations for leaders to think about as they shepherd technology implementation efforts. Find the Modern CTO Podcast on Apple Podcast, Spotify, or wherever you get your podcast.

When you think about tackling complex home improvement projects, the Home Depot likely springs to mind. But what complex AI and ML problems does the Home Depot face while helping you with your projects? Find out today when we talk with Wei-Ming Ke, Senior Director of Data Science at the Home Depot. Welcome to Me, Myself, and AI, a podcast on artificial intelligence in business. Each episode, we introduce you to someone innovating with AI. I'm Sam Ransbotham, Professor of Information Systems at Boston College.

I'm also the guest editor for the AI and Business Strategy Big Idea Program at MIT Sloan Management Review.

And I'm Shervan Kodabande, senior partner with BCG, and I co-lead BCG's AI practice in North America. And together, MIT SMR and BCG have been researching AI for five years, interviewing hundreds of practitioners and surveying thousands of companies on what it takes to build and to deploy and scale AI capabilities across the organization and really transform the way organizations operate.

Today, we're talking with Wei-Ming Ke. She's the Senior Director of Data Science and Machine Learning, Products, Marketing, and Online at The Home Depot. Wei-Ming, thanks for joining us from my hometown, actually. Welcome. Glad to be here. Thanks, Sam. Can you tell us a bit about your current role at Home Depot?

Yeah, so I support this awesome team that has data science and products for overall online and marketing. And there's many challenging problems that we are solving, right, for improving the digital experience for our customers. So I'm super excited. I'm not a DIY person, so every day is a learning experience for me as well.

Yeah, customers need help with so many different types of projects. It seems overwhelming to think about narrowing that down to find specific products that would help them. So how is the Home Depot using AI to help with those projects?

That's a question our teams continuously reflect on. These are very specialized categories, right? And sometimes we need to have other business partners involved as well. There is a particular domain knowledge about appliance or flooring or even plumbing, electrician. When we have machine learning algorithms, if we have enough data, we can typically solve a lot of these problems. But

A lot of times we don't have enough data for the niche problems that we're solving.

When we're going down to the detail of a specific department in that specific category in that plumbing, we talk about PVC pipe. How do we do recommendations the best way? I think a lot of our merchant expertise knows what should go into the recommendation for that particular product. But we have over 2 million products online. How do we train the machine correctly to serve that in a scalable way is really the key.

First of all, we need to make sure we are solving the actual true customer pain point and really aligning around data scientists, user experience, product engineering, this really cross-functional team aligning the goal together.

One of the examples is we have this project guide recommendation, and we also serve a snippet of the difficulty level of that project. And we also serve algorithms in real time identifying potentially what is the project you're working on. So if you're searching for mirror, you're searching for some of the tools and hooks, then we think you probably need some guide about installing a mirror system.

These are things that our customers are facing every day, especially when we're at home now a lot more than before. Literally every day you can think about things could be improved. We definitely feel the responsibility to help our customer to get the help they need. Even just when they search, we need to provide that specific product they're looking for.

Trevor and I were just literally talking about how we're sitting around at home and seeing more things that need to be done now that we're home more often. Lots of what you've described I might call sort of episodic, like someone's at a search and they're trying to find something and they're doing something specific. But you have a larger relationship with customers. The search process might be improving an existing way of searching.

But can you tell us a little bit about what you're trying to do with multiple searches and longer customer lifetime experiences? Absolutely. We certainly care about and wanted to really improve the search relevancy, recommendation relevancy. And every time when people landed on our sites to provide a better experience, these projects, sometimes it takes multiple sessions, multiple days, multiple weeks, and

So it certainly is a customer journey. So we do want to remember as much as possible where the customer stopped. What is in the cart? What are some of the prior searches? What are some of the prior visits? And did this customer actually click on some of the email that we sent? Or outside of Home Depot engagement, other website, about some of our marketing messages? It's a holistic experience.

The more we understand about holistically where the customers is in their journey, the better we can serve them. Getting this holistic understanding seems complicated. So what infrastructure and project management is getting that understanding require? It takes a big effort of engineering to change some part of our infrastructure to accommodate that new algorithms that we're delivering. And the algorithms is already being developed offline. And we know that

This is also something we want to embed it into our search experience to serve it to our customer. But initially when we designed this, it takes engineering an estimated six to 12 months to deliver that change because it's a huge change. The algorithm iteration also takes months to be developed. But when we look at the roadmap, when we actually stack them up,

This will take years to get there. So how do we get there within actually next 12 or 18 months is the challenge to really see as early as possible the test. What is the extremely, extremely light test version that we can get to? To get there much faster, we need to ask ourselves, what is the extremely light version? Maybe we can deliver in 30 days, but we can actually allow the data center to see the

that infrastructure change is not for the final deployment of that architecture to really host the algorithm. It is really just for the testing so that we can actually move a lot faster. And it takes iterations for us to get, it takes time to test, right? These are actually custom experience that is interleaving with data scientists work, user experience work, product and engineering to understand if it's even possible.

It takes a cross-functional team iteratively to move a lot faster, to break down that bigger problem, bigger goals to many smaller ones that we can achieve very quickly. So you mentioned the cross-functional teams. I was kind of curious. You also mentioned customers a lot. But what effects do you see within your organization about places? You know, you've adopted artificial intelligence in some areas. What effects does that have on the organization itself? Are people...

Worried are people happy are they more siloed are they less siloed? Do they have terrible morale or greater morale like what's it doing to the organization when you when you put these things in place?

I think in general, truly everyone believes in the power of machine learning and AI. We have this really the drive to have the human in the loop because domain knowledge in home improvements is extremely important. So this process is really helping the data to be prepared for really unleashing the power of data science and algorithms.

So the algorithm can help, but the algorithm on its own is also quite powerless or it will take it for a long time of unnecessary learning. And this is really fascinating what you guys are doing with all of that. I mean, I have to say I have a bunch of tools, but I'm sure the algorithms would be able to tell me

hey, you actually have a different problem and you're using the wrong tools. And this is why, Sam, my projects are never ending. Because, you know, another reason the projects are not ending is because you don't know what you're doing. It's all the tools, man. It's not mine.

Yeah, we had that. So some of the customers, including myself, right? I don't know what I'm getting myself into. I installed the mirror and the curtain rod in a wrong way and it would just fall, right? And it takes probably times, iterations to get it right. But I think as any Home Depot employee, we feel the responsibility to really deliver that right product to you with confidence.

Basically understanding of this is the right project that you can do it DIY or you may want to consider, you know, services provided to you. I have a pseudo technical question for you. As organizations think about investing in these kinds of capabilities and building the right teams around it, do you feel it's more a data science approach?

investment and hiring of data scientists and data science capabilities? Or have the algorithms been commoditized enough that it becomes more about connecting and building the right APIs between data to algorithms to production system? And hence, it's sort of a different profile of people, much more engineering oriented than I would say, PhDs in data science. Do you have a point of view on that?

I think probably today the titles may not be indicative in terms of the skill sets needed for the title. So I'm not going to be strictly using the title. But I would say in future, we probably need more of the interdisciplinary kind of role, right? So it's the people who can connect the dots because...

We don't necessarily want to always have the PhD scientists to create customized solutions for many of the problems that we're solving. And as machine learning algorithms getting more commoditized and accessible, that is not the key to the success. The key to success is how do you feed the data? What type of data did you feed it to? How do we not do it?

repetitively and a lot of redundancy, right? You do it in parallel to solve similar problems. The way we see it is how do we really host that solution, feed with the right data, build it once and use it many times in a scalable way. We also understand the data science platform will help us to have the data scientists focus on

the right problems and right step of the problem, right? That step may not be creating a new algorithms. That step could be helping our product team, helping our business to understand what is the right problem? How do, what is possible, right? So there's a slight role change in whichever title they're in, but collectively we're going to build

one solution to help serve many of the machine learning applications and help us be smarter making, whether it's assortment choices, pricing choices, you know, could be product collection, selection choices, and providing to search results in a very scalable way. So I don't know whether I exactly answered your question.

I think what I'm hearing is you're saying it's going to evolve to be much more about connecting the dots and really stepping back and saying, what does it take to

to get value, whether it's for merchandising or pricing or marketing? And hence, what do I need to connect to what much more so than how do I improve the algorithmic efficiency of this model by 1%? It's much more about connection. Sometimes the business area to improve that model with 1% is needed. In the area of search, it's needed, right? Because it's a very deep problem

It has very specialized techniques to solve it. And it takes a combination of search algorithms and search platform integration to solve it. These are the areas that we need to go deep. But many of the problems will see a tremendous value to go wider and consolidate to have better solutions in integration. For Home Depot, we have over two-thirds of their revenue is influenced by search, right? So...

the traffic and the amount of impact it will make basically requires and that can actually reflect that 1% to be very impactful. Other areas, you may not need this kind of going very deep and having a very specialized team to do it. Yeah, thanks for correcting me on that. Actually, I think it's very well said. It's integration is one axis and then depth is another. Well, I mean, you clearly have a great background to contribute to both the integration and depth axes of AI problems.

Can you tell us a bit about that background? What brought you to the Home Depot? I think my career is probably a series of happy accidents. And starting from 19 years ago, I came to the U.S. for grad school. In my last year of my PhD, I took this data mining class. That's from Professor Chris's philosophy. That data mining class started my journey in data mining and machine learning. So I since then worked on a wide variety of interesting problems from

Super computer resource optimization. These are, you know, enterprise social network analysis and pricing problems, marketing problems. And today, some of the, you know, very challenging e-commerce problems that we're solving. My first job in IBM, I was in the service department, part of research department. But back then, IBM was 50% of their businesses around service.

After that, I had the opportunity to work in a startup, which is very different. I remember I was asked, I said, why do you consider from IBM to a startup like 50 people? I really wanted to experience that culture and the type of problem is very different. I learned so much building things in production, which I'm still thinking is a very rewarding experience today, right?

And then I worked in financial industry as well, which is actually another accident. Didn't plan to go into financial industry, but I guess it's hard to avoid because I'm in New York. It's a very, very good experience in the middle between IBM research and a startup. Very fast paced with great culture solving very interesting problems, having access to a huge number of

problems, but a huge set of data as well to understand the customer's interest and really serve them the best in a serendipity way. But Home Depot, I think it is going to be the closest to where I really love because it's influencing consumer behavior. It's really impacting hundreds of millions of people's everyday life. And I dreamed about this and it's truly making those impact. It's really powerful.

That for sure sounds very rewarding and eventful. Wei-Ming, I want to take us back to a comment you made about transitioning from research

to a fast-paced environment and putting things in production. Can you comment a bit about what that is like for folks that are moving from a highly, highly academic, very research-oriented, like pushing the boundaries and the frontier to an environment where you're trying to work in a context of...

a company's starting point and challenges and getting to value. What are some of the lessons learned there that you think is helpful to keep in mind? I think the most important thing is the reward system changed, right? So when you're a researcher,

It's very rewarding, but it's a different kind of metric, right? So you're rewarded by working with extremely talented people. These are people who later on go to great companies and working on very challenging projects and contributing to the society.

You're rewarded by the number of publications and patents. And I still have my patent plague, you know, from IDM and not on the wall, but it's a very rewarding experience from that rewarding system. When I joined the startup company,

I think I didn't appreciate, but the rewarding system, it's also very rewarding. That is actually pushing the code into production and seeing the problem that was specifically working on this real-time bidding for these ads. It's very fast-paced to deliver the code, to deliver the new algorithms, and to test and to iterate very fast.

It's not going to be measured by papers or publications and even actually the people you're surrounded, how they're recognized. It's rewarded by reading the results and how quickly we can ship and how quickly we can react to some of the new requirements provided by our customers. So

I think that was really a shift. We need to quickly shift how you're looking at those experiences and really react to those rewarding systems. It's actually quite interesting because the whole domain of what we're talking about, AI and machine learning, is about feedback. So, you know, it's algorithmic feedback, but you're also saying process feedback and user feedback and market reaction.

I think that the team success is very, very important. And throughout the years that we have trying to figure out how do we really create an environment that helps creating innovation, creating innovation driven by machine learning and data science to be successful in the organization. That has been...

one of the key metric in the reward system because we know it's going to be helping us to be even more successful in the ultimate goal we are driving. Ultimately, it's going to be well received by our customer because us customers, having them happy is the ultimate success for the business too.

But one more thing added is to have the team that is successful, right, to make it happen. And my job is probably the most contribution is I hope that I keep them happy and excited about the problems they are solving and hopefully creating that environment that help those scientific dreams to be realized by, you know, the rewarding system is seeing our happy faces from the customer.

Many thanks. You mentioned both depth and integration, and clearly Home Depot is fortunate to have someone like you that excels at both the depth and the integration part. We really enjoyed talking with you and learning about your background and learning about Home Depot today. Thanks for taking the time to talk with us. Thank you for inviting me. It's a very nice conversation. So that was quite an insightful conversation, Sam. What did you think? What resonated with you very strongly?

Yeah, her enthusiasm for the problem really showed. And this idea of the reward structures and how every problem that she worked on, even in different organizations and in different areas, she had to be very careful about tying the incentives and the reward structures to the problems at hand. And I was surprised at the variety of different feedback loops that that created. I think that's also the first thing that stood out for me.

And also, you've got to be so much more, you know, focused on getting it out to production, not letting perfect be the enemy of the good, and also incentivizing your teams who also at some point, you know, came from an academic background to sort of adjust to this new reward mechanism.

I know you like to call me the academic Sherman, but I could see the appeal of getting some fast feedback on things. We work on projects, even the projects that you and I work on. They take a full year from the time we go from surveys to interviews through a research product. She's talking about changing things and getting feedback immediately. I'm jealous. That was pretty beautiful.

Yeah. And it's actually when you talk to data scientists, like that's really what they love about their jobs, the ones that are focused in sort of building solutions that go into production. And then I also like that she was quite cognizant of the importance of it's not just about getting some solution to production. I mean, it has to be good and it has to be efficacious. And there are times where the algorithmic

efficacy is really, really important. So you've got to sort of be able to understand which situation you're in, which also, to me, opens up a dialogue about the skill sets and the attributes of a successful AI specialist or data scientist that not only they need to have very solid technical skills and pedigree and background and all that,

And you're also foreshadowing because we know that PepsiCo is coming up next episode and the variety of talents needed to solve problems also comes out very strongly in that discussion. That was a good segue. Today's discussion of talent needs segues well into our next episode with Colin Linehan from PepsiCo as he talks about the technical, organizational and commercial talent PepsiCo needs to accomplish its objectives. Please join us.

Thanks for listening to Me, Myself, and AI. If you're enjoying the show, take a minute to write us a review. If you send us a screenshot, we'll send you a collection of MIT SMR's best articles on artificial intelligence, free for a limited time. Send your review screenshot to smrfeedback at mit.edu.