Independent consultant specializing in Knowledge-Centric Machine Learning Systems (KMDS), scalable analytical infrastructure, and robust, auditable AI. I design production-ready alternatives to costly enterprise ML platforms, delivering high-integrity models with built-in data lineage.

• Methodology: KMDS, Knowledge Graphs, Data Lineage Tracking, Model Auditability & Reproducibility.
• Modeling: Application of Statistical Learning Techniques to develop Business Applications, Graph ML, Explainable AI (XAI), Discrete Optimization.
• Infrastructure: Enterprise ML Architecture, High-Velocity Analytical Pipelines, Platform Offboarding.

I am the creator and principal maintainer of the Knowledge-Centric Machine Learning Systems (KMDS) framework. KMDS is an open-source methodology engineered to deliver ML products with auditability, transparency, and reproducibility built in from day one.

• The Problem: Operational data is rarely clean, static, or friendly to automation.
• The Solution: KMDS captures and structures analytical knowledge, feature definitions, and data dependencies to ensure solutions remain sustainable long after initial deployment.

👉 Explore the Core Repository: View KMDS Framework

👉 View the KMDS Examples Repository View KMDS Examples Repository — A set of repeatable enterprise-grade operational analytics workflows built using open-source KMDS pipelines.

📈 tseda: Enterprise-Grade Time Series Signal Decomposition & Automated DiagnosticsA high-fidelity Python framework that automates time-series preprocessing, SSA parameter selection, and decomposition. It provides a bridge between automated Notebook pipelines and interactive Plotly dashboards, with built-in auditing through KMDS integration.

👉 Explore the Core Repository: View TSEDA

• 25+ Years of Engineering Maturity: Developing and scaling data-centric software applications across Retail, Financial Services, Telecom, Transportation, and Government sectors.
• Core Career Timeline: 10 years dedicated to software application development for scheduling and capacity management; 15 years focused strictly on machine learning, information retrieval, data mining, and discrete optimization.
• Academic Foundation: PhD in Machine Learning. Selected publications spanning scalable statistical learning, graph-oriented analytical systems, and enterprise-scale ML infrastructure are indexed on Google Scholar.

I am available for independent consulting engagements, technical advisory roles, and fractional architecture assignments. I partner with:

• Teams looking to bypass or migrate away from rigid enterprise ML platform vendor lock-in.
• Organizations needing deep, hands-on modeling support (classification, regression, survival analysis, panel data).
• Operations and finance leaders requiring clear data lineage and explainable automated decisions.

📫 Connect with me:

• Website: r2-ds.com
• LinkedIn: Connect on LinkedIn
• Publications: Google Scholar Profile