Sholto Armstrong
github profile: https://github.com/sjnarmstrong
Hi, I’m Sholto, a seasoned Machine Learning Engineer passionate about developing cutting-edge AI and data analytic solutions. I’ve had the pleasure of working on a range of impactful projects across various industries.
Currently, at **Capitec Bank**, I’ve developed and productionized a Rules Engine for credit granting and fraud detection. Additionally, I’ve consulted on AI projects related to customized RAG Chatbot systems, focusing on improving system architectures and performance.
My previous role at **IoT.NxT** (a subsidiary of Vodacom/Vodafone) involved leading a team to create scalable AI and data analytic solutions for IoT applications. I enhanced data analytics capabilities, streamlined agile processes, and optimized CI/CD pipelines for better efficiency.
I hold a Master’s degree in Computer Engineering with a focus on Scene Understanding from the **University of Pretoria**, where I also completed my Bachelor’s and Honours degrees with distinction.
Outside of work, I enjoy gymming, surfing, and solving Rubik’s cubes. These activities keep me motivated and help me tackle challenges with enthusiasm.
Accepted Talks:
Building a Decisioning Engine for Data Scientists: A Practical Guide
Machine learning offers a modern replacement for human-curated predictive decisioning. However, in practice, predictive rules manually created from expert domain knowledge remain extremely relevant in many industries, most notably finance. These rules are straightforward, highly explainable, and enable experts to incorporate valuable domain knowledge. However, the open-source ecosystem until recently, lacked comprehensive tooling for creating decision flows that can be operationalized following modern-day machine learning best practices.
In this talk, we will introduce a new open-source decisioning framework built on Hamilton, a versatile framework designed to streamline the creation and management of dataflows using standard Python functions. Hamilton simplifies the development process by converting functions into nodes in a Directed Acyclic Graph (DAG), allowing for efficient execution and visualization of decision flows. Our new open-sourced framework enables scientists to create rules around Statistical, Machine Learning, and Large-language models. We will showcase the framework's ability to address fraud detection, credit granting, and integration with LLMs. This session is tailored for decision creators (e.g., data scientists, decision scientists, and data analysts), and operations engineers.
The talk will delve into the key components of our Python-based decisioning solution applicable to finance, including decision trees, credit risk scorecards, and decision tables. We will emphasize using Directed Acyclic Graphs (DAGs) to achieve interoperability, traceability, and visual insights into decision-making processes. We will then show how these decisioning processes can be productionised for real-time and batch use cases. The talk will provide listeners with practical insights for developing decisioning flows using best practices.
