Dave McComb: Semantic Modeling for the Data-Centric Enterprise – Episode 29

Dave McComb During the course of his 25-year consulting career, Dave McComb has discovered both a foundational problem in enterprise architectures and the solution to it. The problem lies in application-focused software engineering that results in an inefficient explosion of redundant solutions that draw on overlapping data sources. The solution that Dave has introduced is a data-centric architecture approach that treats data like the precious business asset that it is. We talked about: his work as the CEO of Semantic Arts, a prominent semantic technology and knowledge graph consultancy based in the US the application-centric quagmire that most modern enterprises find themselves trapped in data centricity, the antidote to application centricity his early work in semantic modeling how the discovery of the "core model" in an enterprise facilitates modeling and building data-centric enterprise systems the importance of "baby step" approaches and working with actual customer data in enterprise data projects how building to "enduring business themes" rather than to the needs of individual applications creates a more solid foundation for enterprise architectures his current interest in developing a semantic model for the accounting field, drawing on his history in the field and on Semantic Arts' gist upper ontology the importance of the concept of a "commitment" in an accounting model how his approach to financial modeling permits near-real-time reporting his Data-Centric Architecture Forum, a practitioner-focused event held each June in Ft. Collins, Colorado Dave's bio Dave McComb is the CEO of Semantic Arts. In 2000 he co-founded Semantic Arts with the aim of bringing semantic technology to Enterprises. From 2000- 2010 Semantic Arts focused on ways to improve enterprise architecture through ontology modeling and design. Around 2010 Semantic Arts began helping clients more directly with implementation, which led to the use of Knowledge Graphs in Enterprises. Semantic Arts has conducted over 100 successful projects with a number of well know firms including Morgan Stanley, Electronic Arts, Amgen, Standard & Poors, Schneider-Electric, MD Anderson, the International Monetary Fund, Procter & Gamble, Goldman Sachs as well as a number of government agencies. Dave is the author of Semantics in Business Systems (2003), which made the case for using Semantics to improve the design of information systems, Software Wasteland (2018) which points out how application-centric thinking has led to the deplorable state of enterprise systems and The Data-Centric Revolution (2019) which outlines a alternative to the application-centric quagmire. Prior to founding Semantic Arts he was VP of Engineering for Velocity Healthcare, a dot com startup that pioneered the model driven approach to software development. He was granted three patents on the architecture developed at Velocity. Prior to that he was with a small consulting firm: First Principles Consulting. Prior to that he was part of the problem. Connect with Dave online LinkedIn email: mccomb at semanticarts dot com Semantic Arts Resources mentioned in this interview Dave's books: The Data-Centric Revolution: Restoring Sanity to Enterprise Information Systems Software Wasteland: How the Application-Centric Quagmire is Hobbling Our Enterprises Semantics in Business Systems: The Savvy Manager's Guide gist ontology Data-Centric Architecture Forum Video Here’s the video version of our conversation: https://youtu.be/X_hZG7cFOCE Podcast intro transcript This is the Knowledge Graph Insights podcast, episode number 29. Every modern enterprise wrestles with its data, trying to get the most out of it. The smartest businesses have figured out that it isn't just "the new oil" - data is the very bedrock of their enterprise architecture. For the past 25 years, Dave McComb has helped companies understand their data, discovering along the way the importance of adopting a data-centric mindset that reveals the essential nature and the true value of this precious asset. Interview transcript Larry: Hi, everyone. Welcome to episode number 29 of the Knowledge Graph Insights Podcast. I am really happy today to welcome to the show Dave McComb. Dave, I think it's safe to say he's a legend in the ontology and knowledge graph worlds. He's the author of three books. One early book called Semantics in Business: The Savvy Manager's Guide, which was probably ahead of its time, which is fine. Dave's that kind of guy. He also wrote the books Software Wasteland and The Data-Centric Revolution, which set the problem that we have in current enterprise architectures and the proposed a solution. Those, by the way, are both under revision. By the end of 2025 or so, we should see new editions of those. Welcome, Dave. Tell the folks a little bit more about what you're up to these days. Dave: Great. Thanks, Larry. Well, we're still running a company here. We have Semantic Arts, probably it's about 30 employees. 20 ontologists and five semantic developers doing God's work, making companies more data-centric. That's what we do now. We go into companies, mostly medium to large-sized companies, and help them. Dave: What we've done since the publishing of the book, we started doing it around the publishing of the book, is just figuring out a methodological, and fairly safe and incremental way to get there. Because I think a lot of companies are burned out from so-called legacy modernization projects and digital transformation projects that didn't go well. There's a lot of scar tissue there. We've figured out a way to, first, move some of your data, get it into the graph, get you used to it. Then start moving more, and then more functionality, and just gradually get people there. Larry: That's the classic smart consultant, baby steps, proofs of concept. Dave: Yeah. Larry: Small work out there. Dave: Yeah. Larry: Hey, let's back up a little bit and talk about, because I'm going to guess that many if not most of my listeners are familiar with you. But for those who aren't, can you talk a little bit about the philosophy? Because you've got a well-articulated philosophy set out in two books about the problem this application-centric quagmire that enterprises got themselves into, and then the data-centric way. Can you talk a little bit about the ... I'd love to know where the idea occurred to you, how you identified the problem, and then a little bit about the two books. Dave: Yeah. I started my career with Arthur Anderson, the accounting firm, but they had a consulting division which originally was just called the Administrative Services Division. How innocuous. We worked with the accountants a lot. Then it, as we know, eventually grew into the consulting division, which was Arthur Anderson Consulting, which is now Accenture. They grew like crazy. But back in those early days, we built and implemented mostly accounting systems. I had a career of going around the world, implementing, often building from scratch because it was early days, accounting systems. Including two pretty major full-function ERP systems built from the ground up, and one of them in multi-currency. Pretty sophisticated. Dave: It's two things I thought I knew at the time. One, I thought I knew accounting and accounting systems. And I thought I knew the right path for building enterprise applications. But then, right as I was leaving and then as I was doing some independent work on the side, I started to see what was actually going on. That companies were just implementing system, after system, after system. You'd go into a client and they'd have a dozen inventory control systems. You'd go, "Wow, not only do you have a dozen of them." By the way, I'm going to update that and I'll give you some metrics about how many systems most of our clients currently have. Dave: What bothered me more was they're all completely arbitrarily different. Not only did every single one of them, which had hundreds or thousands of tables, and each table had dozens of columns, and every one of them had some totally made up name. Some of them, German acronyms, all kinds of stuff. They were even structured differently. You'd go, "Wow. What would cause several different smart people to design an inventory control system and have them come out that different?" We studied database design, third normal form, and all that. If you'd laid out the problem exactly the same, you'd do third normal form, and you'd get to the same answer, but they were not starting from the same place. Then you go, "Wow. Why not? What's going on here?" This is the early '90s. Dave: This is back before the World Wide Web, you would have to go to the library to do research. And so we'd go to library, and find magazine articles, and photocopy them, and all those. I know I still have a three-ring binder. There were four articles at that time about applying semantics to information systems. We had devoured, I think, everything that was known at the time. Now, of course, if we did a Google search, there probably was other stuff that we didn't find. We invented this thing we called semantic modeling and said maybe, if you started from what things really mean, you'd actually figure out that inventory actually really means widgets and bins, whatever it is. But you'd hopefully start from the same place and end in the same place. Dave: Yeah, that was my observation and how we got into this. A few minutes ago, I'd promised I'd come up with some metric. As we've been going from client to client now, and this is not an exact metric but it's close enough to be scary, take the number of employees you have in your company and divide it by 10, that's probably about how many applications you're currently managing. Larry: Wow. Dave: Think about it.