Specializing in exploratory analysis, predictive modeling, and data driven storytelling. From customer churn and fraud detection to energy forecasting and industrial analytics, turning complex data into clear, actionable insights.
A data storyteller with an engineering mindset
I'm Owen, I specialize in transforming complex datasets into clear insights, intuitive visualizations, and practical solutions.
With experience across analytics, machine learning, and technical problem-solving, I bridge the gap between raw data and actionable business intelligence. My projects span predictive maintenance, fraud detection, energy forecasting, and customer analytics.
ResumeReal-world projects solving complex business challenges
Forecasted household energy consumption using historical data and SARIMA, uncovering trends, seasonality, and patterns to optimize energy usage.
Predicted solar power generation using weather data and a Random Forest model. Performed data preprocessing, analysed feature importance, trained the model, and evaluated its performance.
Predicted machine failures using the AI4I dataset with a full workflow: cleaning, EDA, and machine learning classification, providing actionable maintenance insights.
Predicted customer churn using machine learning on the Telco dataset, highlighting key drivers and enabling actionable retention strategies.
Exploratory analysis of real Wind Turbine SCADA data, visualising performance and comparing actual vs theoretical power using Python.
Detected fraudulent credit card transactions using Isolation Forest and Random Forest, highlighting key patterns and features for actionable insights.
Detected anomalies in industrial sensor data using Isolation Forest, enabling identification of unusual machine behaviour and supporting predictive maintenance.
Analysis of public transport usage using 2019 aggregated data and 2022 journey-level records to identify trends and behavioural changes.
Analysed European Air Traffic Control (ATC) pre-departure delay data from 2017 to 2023 to identify temporal trends, airport-level performance, and the impact of COVID-19 on delay behaviour.
End-to-end analysis of the Superstore dataset, including data cleaning, exploratory analysis, visuals, and business insights.
Exploratory analysis of the UK Department for Transport's 2021 road safety dataset. Identified accident trends, severity factors, weather influence, and time-of-day patterns.
Exploratory data analysis of student exam scores using Python to identify performance trends, statistical patterns, and key influencing factors.
Continuously learning from industry-leading platforms
Have a project in mind or want to discuss opportunities? I’d love to hear from you.
