Book Image

AI and Business Rule Engines for Excel Power Users

By : Paul Browne
Book Image

AI and Business Rule Engines for Excel Power Users

By: Paul Browne

Overview of this book

Microsoft Excel is widely adopted across diverse industries, but Excel Power Users often encounter limitations such as complex formulas, obscure business knowledge, and errors from using outdated sheets. They need a better enterprise-level solution, and this book introduces Business rules combined with the power of AI to tackle the limitations of Excel. This guide will give you a roadmap to link KIE (an industry-standard open-source application) to Microsoft’s business process automation tools, such as Power Automate, Power Query, Office Script, Forms, VBA, Script Lab, and GitHub. You’ll dive into the graphical Decision Modeling standard including decision tables, FEEL expressions, and advanced business rule editing and testing. By the end of the book, you’ll be able to share your business knowledge as graphical models, deploy and execute these models in the cloud (with Azure and OpenShift), link them back to Excel, and then execute them as an end-to-end solution removing human intervention. You’ll be equipped to solve your Excel queries and start using the next generation of Microsoft Office tools.
Table of Contents (22 chapters)
Free Chapter
1
Part 1:The Problem with Excel, and Why Rule-Based AI Can Be the Solution
5
Part 2: Writing Business Rules and Decision Models – with Real-Life Examples
9
Part 3: Extending Excel, Decision Models, and Business Process Automation into a Complete Enterprise Solution
13
Part 4: Next Steps in AI, Machine Learning, and Rule Engines
Appendix A - Introduction to Visual Basic for Applications

Summary

The topics we covered in this chapter were the idea that ML is as simple as drawing a line on a graph, with the learning piece being teaching the machine to find where that line should go. We walked through a simple learning model based on naïve Bayes, and in the notebook that implemented the model, we highlighted where we could drop in other algorithms. We ran that notebook on Azure ML and generated a graph to test whether our predictions were in line with what we expected.

Exporting our trained model as a PMML file, we included it in a rules-based decision model. We updated our previous chocolate bar recommendation service using this technique and showed that it was very feasible to build a model combining the best of each type of AI. Finally, we discussed our options as Excel power users for executing these combined models.

This theme of introducing advanced topics to explore further continues in our next and final chapter. That extends several topics we glimpsed...