Machine Learning with Python

**Improving Office in Franklinton** Physical location: Improving Office 330 Rush Alley Suite #150 Columbus, OH 43215 Schedule: 6:00 p.m.: Socialize, eat, and drink. Improving will be providing pizza and beverages. 6:30 to 8:00 pm. Main meeting and presentation(s). Topic: This month John Lairson will share a notebook describing the Alpaca (Paper) Trading API and discuss different algorithms for evaluating stock trades. We meet on the last Monday of each Month. Presentations are given by members and friends of this group. If you would like to do a presentation (small or large) on a python topic, please contact Central OH Python at centralohpython@gmail.com

**Latest Dojo Location!** **Knotty Pine Brewing** 1765 W 3rd Ave, Columbus, OH 43212 We're going to try a new dojo location for a few weeks and see how it works Dojos are informal Python group study sessions where everyone interested in Python gathers to learn about Python, help others with Python, or just hang out. Everyone is welcome from Python beginners to experts. Bringing a laptop is encouraged (we'll have extension cords and power strips). If there's something you want to learn leave a comment on this invite so we can plan ahead. We're looking for speakers for our Monthly Meetups! Fill out the form if you are interested in presenting to the Python Community. https://forms.gle/ehSfUAC2WgR34Crq9

Join us for a practical, beginner-friendly guide to choosing the right large language model. We’ll compare major models like ChatGPT, Claude, Gemini, and Llama, talk about when to use hosted APIs versus local models, and break down the tradeoffs around cost, speed, quality, privacy, context windows, coding ability, and reliability. You’ll leave with a clearer mental model for picking an LLM based on your actual use case instead of hype, benchmarks, or brand names. No deep AI background required. LOGISTICS AND PARKING: The talk starts at 7:00 PM. The first half hour is reserved for everyone to get set up and mingle. Free pizza and drinks! The cheapest parking option is to find street parking, which will only cost you a few bucks. Otherwise, park in the nearby veteran's museum lot for $8. It's highly recommended you avoid the nearby $15 garage parking.

Join the Columbus AI community for our quarterly gathering — a casual, community-focused evening where everyone has a chance to share, learn, and connect. These open mic–style events give anyone in the community up to **5 minutes** to present a project, share a tool, pose a question, or offer a perspective on the evolving AI space. No slides required — just a welcoming space to exchange ideas and keep the local AI conversation moving. If you’d like to take the stage, message \*\*Chris (the organizer)\*\*with a **title and short description** of what you’d like to share. Whether you’re deep in the field or just getting curious, come connect with others building and exploring AI in Columbus. Sponsored by [Transform Labs](https://www.linkedin.com/company/transformlabs/) Sign up also accessible via [Transform Labs Luma](https://luma.com/transformlabshq)

Customer identity resolution becomes increasingly complex as organizations scale across multiple systems, regions, and data formats. Traditional rule-based approaches often fail to keep up with data variability, require constant manual tuning, and struggle with real-time processing needs. This session presents a practical approach to building a scalable identity resolution pipeline using AWS services and modern AI techniques. The architecture combines data ingestion through Amazon S3 and AWS Glue, transformation pipelines using Spark on EMR, and machine learning models deployed via SageMaker for entity matching and standardization. Graph-based relationship modeling is implemented using Amazon Neptune to improve resolution accuracy by incorporating household and shared attribute context. We will walk through how machine learning models can be used for name and address normalization, how intelligent blocking strategies improve matching efficiency, and how feedback loops can be introduced to continuously improve accuracy. The session also highlights how serverless components such as AWS Lambda can be used for orchestration and real-time processing. **SPEAKER BIO** Mosaic Syed is a Senior Data Engineering and Cloud Solutions Architect with over 20 years of experience designing and delivering scalable, secure, and high-performance data solutions across global enterprise environments. https://www.linkedin.com/in/mosaic-basha-syed-92300856 **CALL FOR SPEAKERS** Learn more: [https://www.awscolumbus.com/get-involved/](https://www.awscolumbus.com/get-involved/) **THANK YOU** *VEEAM* for hosting our meetup! To learn more about *Veeam*, please visit their website: [https://www.veeam.com/](https://www.veeam.com/) **DIRECTIONS** 8800 Lyra Dr #450 · Columbus, OH go to 4th floor. **Want to sponsor the pizza and/or bar tab?** Please contact me if you would like to sponsor this meetup's pizza and/or bar tab: angelo@mandato.com

We will show how to build custom agents with Microsoft Agent Framework. Attendees will learn how to build and custom host agents when Microsoft Foundry is not a viable option.