HomeSkillsMachine Learning
ExpertAI & Machine Learning

Machine Learning

Expert
11 projects

Applied ML across e-commerce personalization, supply chain optimization, and cloud infrastructure. Built models for customer pattern recognition, product rating analysis, and predictive analytics using Python, TensorFlow, and AWS SageMaker.

My ML work spans the full spectrum from classical statistical models to deep learning architectures. At FLIR Systems, I built a recommendation engine combining collaborative filtering with neural embeddings that increased average order value by 23%. The engineering challenge wasn't the model it was building the real-time feature store that fed predictions in under 50ms at scale.

The cold start problem taught me the most about ML system design. New products and new users have no interaction history, making collaborative filtering useless. I built a three-tier fallback: collaborative filtering for users with sufficient history, content-based filtering using product attributes for new users, and editorial curation for brand-new visitors. As users accumulated signals, they graduated automatically. Measuring quality at each tier guided investment in improving the weakest tier.

Model drift is the silent killer of production ML systems. A model performing excellently at launch degrades gradually as data distributions shift. I implemented continuous monitoring tracking feature distributions, prediction confidence, and outcome accuracy. When drift exceeded thresholds, automated retraining pipelines kicked in. This closed-loop system meant models improved over time rather than decaying.

ML success requires organizational alignment more than technical sophistication. I've seen brilliant models fail because business stakeholders didn't trust them and engineers couldn't explain them. I invested in interpretability SHAP values, feature importance dashboards, decision explanations turning black boxes into understandable systems. When the business can see why the model made a decision, adoption follows.

At FLIR Systems, the recommendation engine combining collaborative filtering with neural embeddings increased average order value by 23%, and the real-time feature store fed predictions in under 50ms at scale. The cold-start fallback, with collaborative filtering, content-based filtering, and editorial curation, ensured that new users and new products always received relevant recommendations.

The customer data platform at FLIR Systems unified e-commerce, CRM, and telemetry data for churn prediction, segmentation, and personalised activation, processing millions of records with automated retraining pipelines. The model drift monitoring I implemented tracked feature distributions and prediction confidence, triggering automated retraining when drift exceeded thresholds, which reduced model degradation incidents by 70%.

Explore the Full Portfolio

This is the complete portfolio of Sufi Khan Sulaiman, a technology leader specialising in B2B commerce and digital automation. Start from the Home page for the overview, then move through two decades of career experience across FLIR Systems, Lorex Technology, and 1c Platform, and the full catalogue of project case studies spanning headless commerce migrations, AI recommendation engines, and multi-channel fulfilment systems.

The skills and certifications page maps the technical and leadership capabilities behind the work, while the articles and the knowledge base break down the thinking into actionable frameworks. For hands-on learning, the tutorials and applications sections cover practical builds from front-end fundamentals to full-stack web apps.

For consulting engagement, the expertise page outlines service offerings, the ecommerce hub covers platform architecture and automation strategy, and the ecommerce guide (PDF) is a downloadable 55-page field manual. When you are ready to talk, the contact page is the direct line.