Projects
Most projects are in various stages of stealth mode, but a few are visible to the public.
Beat the Table
We are looking at a software system designed to analyze certain casino games and generate a winning strategy. Most games have a house advantage that cannot be beaten, but some stateful games, such as Blackjack, can definitely be beaten. There are several other games, which are quite complicated, but which can also be beaten.
Wizard
We created a software system named Wizard (weighted index zero-based regression discriminator) that successfully predicts NFL American football results. Successful here means an accuracy of greater than 60% against the Vegas point spread line. This system was featured weekly on a local NBC TV affiliate sports program.
Sorcerer
Sorcerer is a system that predicts the total number of points scored in an NFL football game, for use in betting over-under results. Sorcerer uses a neual network and bio-inspired optimization. Early versions of Sorcerer predict with approximately 64% accuracy.
Publishing
Every now and then we publish technical papers that are spin-offs from our research. Two examples:
- Linear Support Vector Regression Using C# with Particle Swarm Training, Visual Studio Magazine, June 2025
- R Programming Succinctly, Syncfusion Publishing, Morrisville, NC, 2020