Custom software
We build operational tools, integrations, and applications around your workflows, data, and business requirements.
LOGARITHM builds custom software, AI and machine learning, optimization systems, and analytics tools for complex business operations.
Discuss your projectWe build operational tools, integrations, and applications around your workflows, data, and business requirements.
We develop prediction, classification, and computer vision models, then integrate them into practical business systems.
We engineer scheduling, resource allocation, and decision systems around real constraints and measurable objectives.
We connect data sources, build processing pipelines, and turn complex information into clear decision tools.
Understand the workflow, the people, and the problem worth solving.
Define the constraints, the economics, and the measures of success.
Engineer a focused system around the requirements that matter.
Evaluate the result against the agreed objectives and refine it.
Applied work across healthcare AI, computer vision, predictive modeling, and optimization.
Led development of an AI/ML backbone for improving patient triage and subspecialty referral within a major health system.
Developed a YOLO-based computer vision system and supporting meta-models that reduced counting error and error variance by more than 60% for a leading US poultry company.
Developed symbolic regression and grammatical evolution frameworks for efficiently searching complex model spaces and discovering predictive structures.
Developed an AI clinical simulation platform with faculty-authored virtual patients, spoken interviews, deterministic fact disclosure, and transcript-backed debriefs. Earned 2nd Place in the TwinVerse Track at Rutgers Health Hack 2026.
Built a genetic programming pipeline that automatically generates, optimizes, validates, and combines predictive models for financial market behavior.
Designed a multi-layer neural network architecture that distributes learning across feature and time dimensions before aggregating predictions into a unified meta-model.
Email a brief outline of what you’re building or trying to improve.
logan@logxco.com