I'm Ho Daniel Khuu data scientist & and full-stack developer

ChallengeMunicipal planners needed to anticipate pollution events fast enough to warn residents and adjust traffic flows.

ApproachBuilt an ensemble forecasting pipeline that cleanses multi-source sensor data, engineers weather features, and serves predictions through a containerised API.

OutcomeDelivered 94% accurate forecasts powering daily dashboards and automated alerts across three city districts.

ChallengeEnterprise leaders wanted a measurable way to improve employee wellbeing and reduce sick leave.

ApproachBuilt cross-platform apps, telemetry pipelines, and nudging mechanics that turned wellbeing goals into daily habits.

OutcomePilots reported higher engagement, positive sentiment, and downward trends in sick leave across teams.

ChallengeStakeholders needed reusable patterns to explore heterogeneous datasets, from text corpora to mobility logs.

ApproachRan structured experiments combining classical ML, topic modelling, and recommendation techniques with reproducible notebooks.

OutcomeProvided decision-makers with clear playbooks and code templates to accelerate future data initiatives.