Product LeaderData & ML Platforms
I build and scale data and machine learning platforms. 18 years across e-commerce, adtech and fintech: search, recommendations, customer data platforms. Now building Routekeepers, a two-sided marketplace for permitted land access.
Numbers do the work.
- +20%search customer satisfaction
Multi-intent ranking framework. Takealot.
- 3×recommendation impression share
Flexible context-aware API. Takealot.
- Petabytecustomer data platform
Composable CDP, multi-brand, identity resolution. Takealot Group.
- −15%zero-result searches
Organic ranking model, Mr D groceries. Takealot Group.
- 80% → 30%GeoIP-to-WiFi conversion target
Micro Networks model. Vicinity Media (proof-of-concept).
- 18years
E-commerce, adtech, fintech. MBA. Cape Town.
A project execution framework for machine learning.
Built at Takealot Group to make the gap between exploration and productionisation explicit. The diamond below is the core visual: ideation expands into multiple candidate paths, then contracts into a single productionised model. Click any stage for detail.
The framework is about shape, not duration. Cadence varies with stack maturity, dataset readiness, and modern tooling (synthetic data generation, LLM-assisted prep, foundation-model baselines) often compresses several stages substantially.
Running the 6-month framework in practice surfaced two missing phases. The longer 15-month variant adds these as inline additions to the same diamond — not new structure, just acknowledgement that real ML work sometimes needs a dataset detour and a thinking pause.
- Learning 01Inserted before Generate Training Data
Dataset Exploration Phase
Often the bottleneck isn't the model — it's the dataset. Before committing to model training, generate multiple candidate datasets in parallel and pick the winner. Two evaluation paths: assess them via offline modelling against established metrics (when you'll need a model anyway), or — when the use case is simple enough — serve them directly as an A/B test. A caveat worth stating: if direct-serve datasets are sufficient on their own, you probably don't need a model at all.
- Learning 02Inserted after A/B Test, before retraining
Investigation Buffer
The A/B test doesn't always yield a clear answer. Reserve dedicated time after a test to investigate the result — understand the customer behaviour underneath the metric — instead of forcing immediate iteration. This stops cascading dependencies when an A/B test result requires deeper analysis (e.g. the Category Intent rollout, which needed investigation before promotion).
Both additions extend the project shape — a dataset arc up front, a thinking pause at the end. In practice they can add real time to a programme, though modern tooling (synthetic data generation, LLM-assisted analysis) compresses both phases substantially.
The diamond is calibrated for classical supervised machine learning — train a model against labelled data, evaluate offline, A/B test, productionise. The shape of the work still holds for agentic workflows: same expansion / contraction logic, same need for explicit checkpoints. Several stages just compress or change form.
- Generate training dataPrompt design · RAG corpus · synthetic data
- Candidate Model nCandidate prompts · tool sets · orchestration patterns
- Iterative trainingPrompt iteration · retrieval tuning · tool-spec refinement
- Offline POC evaluationLLM-as-judge · behavioural tests · red-team probes
- A/B test or internal testA/B with completion rate · human eval · latency budgets
- Productionise + stageGuardrails · rate limits · fallback prompts
- Drift monitoring+ hallucination rate · tool-call accuracy · latency
The two learnings (the dataset detour and the investigation buffer) carry over directly. The investigation buffer matters more in agentic work, not less — behavioural failures rarely have a clean numeric answer.
These are the artefacts that typically accompany a project on this framework. Names and roles only — the actual templates and specifications aren't included on this site; they live with the team that adopts the framework.
Career
- 2025 — Present
Founder (Product)
Building Routekeepers, a two-sided marketplace connecting verified riders to permitted land access and route guides. Designed and built the full product and data stack.
MarketplaceData platformProduct - 2024 — 2025
Group Product Lead — Customer Data & ML
Takealot GroupLed product strategy for the customer data platform, CRM, insights and fraud ML across a multi-brand group, while keeping ownership of the ML roadmaps. Led a team of 4 product managers. Defined the architecture for petabyte-scale event collection, sessionisation and multi-model attribution. Established an extensible reporting framework and layered raw → aggregate → datamart conventions, improving data quality and coverage.
Customer Data PlatformIdentity resolutionMulti-brand - 2022 — 2024
Group Product Lead — AI & ML
Takealot GroupOwned ML product strategy for search, recommendations, merchant ML and supply chain ML across Takealot, Superbalist and Mr D. Shipped organic ranking models at Superbalist and Mr D groceries, cutting zero-result searches (by 15% at Mr D) and lifting cart conversion.
SearchRecommendationsML platforms - 2020 — 2022
Product Manager (AI/ML) — Search & Recommendations
Takealot.comOwned the ML roadmap for search and recommendations, prioritised against the portfolio's North Star metrics. Led the multi-intent search framework: +20% customer satisfaction. Led the refactor of "You Might Also Like" (3x share of product page views, 5% to 15%) and launched a flexible recommendations platform for model-agnostic serving and faster experimentation.
SearchRecommendations - 2017 — 2020
Product Lead — AdTech Portfolio
Vicinity MediaOwned strategy for a mobile location-advertising platform across three roadmaps: audience data, out-of-home attribution and ad server/campaign management. Led 2 product managers and defined success metrics for projects and releases. Developed out-of-home attribution linking billboard exposure to in-store visits. Founded the data science function, enabling ML-driven audience targeting and performance optimisation.
AdtechAttributionAudience - 2008 — 2015
Consulting Manager
Cape ValueLed data analysis, market research and statistical modelling engagements, plus strategy and forecasting, for financial services (secured lending, claims management) and public sector (property revenue management) clients.
ConsultingModeling
Selected work, in depth.
- Case 012020 — 2022
A multi-intent modelling framework for search
Reframing ranking from a single black-box model into composable intent models — the FY23–FY25 vision.
SearchML Platforms3-Year VisionTakealot GroupRead → - Case 022020 — 2022
Flexible recommendations: a context-aware API
One API serving every surface — PDP, cart, wishlist, search, home. Context-aware delivery from a composable model library.
RecommendationsPlatform ArchitectureAPI DesignTakealot GroupRead → - Case 032024 — 2025
Composable customer data platform
Petabyte-scale, first-party tracking events, cross-device and cross-brand identity resolution. Multi-brand activation.
Customer Data PlatformData PlatformIdentity ResolutionTakealot GroupRead → - Case 042017 — 2020
Micro Networks: a proof-of-concept for clawing back precise location
A POC model designed to extend Vicinity's existing location accuracy into the 80% of ad requests where users didn't share their coordinates.
AdTechLocation accuracyProof of conceptVicinity MediaRead →