As a data scientist with a rich background in digital marketing, I apply data-driven solutions to real-world challenges in media. With experience in independent roles, I've managed end-to-end processes—from raw data to production models—ensuring impactful contributions for my stakeholders.
A lot of models work. Evaluation metrics tell us which ones work well.
Evaluation metrics describe how well a model predicts on unseen data, and are used in fine-tuning. In the Python package "implicit", the evaluation module returned errors for common metrics, such as Normalised Discounted Cumulative Gain (NDCG).
Predicting inactivity using activity, and the lack thereof
Digital media rely on user activity to determine marketable audiences. Being able to predict churning users allow for retention efforts to be put in place. In this project, I defined churn as a 30-day streak of a logged-out state, or 30-day streak of non-listenership.
Zero to Hero: From raw data to business-ready assets.
At the nascency of this digital radio product, I focused on establishing big data pipelines to meet business needs for reporting, visualisation, and machine learning applications.
Increased profit margins by limiting ad requests to profitable observations.
Supply-Side Platforms manage ad space by deciding which instances of web traffic would be good to show ads to; however, not all traffic is profitable, and sending these instances to the auction (real-time bidding) can be costly.
Integrate 5 Brand Data Sources programmatically to populate reporting records.
Management makes use of spend, revenue, and eCommerce metrics to make marketing decisions. The stakeholders had a preference for tables that could be explored by date range and broken down by date.
Explore trends in mental health report misclassifications to the police as indicators of supplementary social services.
In 2021, the New Zealand Police expressed a need to approach call-outs related to mental health issues. To free up the workload of the police force in that regard, it would be good to explore existing trends on mental health-related issues.
Extract video and channel data from search queries, and store them to a database.
For my first Python project, I wanted to understand popular video topics in a certain niche, and explore Youtube as a data source. One of the largest limitations to the project is the rate limit, which compelled me to consider an ETL process to avoid redundant extraction.
As the Senior Data Analyst, I delivered key results by developing solutions through data and collaborating with various leaders across the business (OneRoof and NZ Herald). These solutions provided clarity and guided decision-making within the company.
May 2025 - Present
Deployed a subscription propensity model using Machine Learning (ML) in Python. This enabled the Subscriptions team to focus resources on users who are highly likely to subscribe.
Developed and optimised data pipelines for OneRoof's app and website data using BigQuery SQL and Dataform. This allowed reports to scale and opened opportunities for behavioural analytics.
Automated the report generation process for ad operations and digital performance using SQL, BigQuery ML, Python, and AI (Gemini). Every week, this delivers a PDF that contains a summary, relevant figures, and recommendations.
Improved users' app experience by developing a cross-platform readership analysis. This lifted the clickthrough on the app.
Designed the analytics tracking and automated testing framework for the NZ Herald App. This smooth tracking rebuild accounted for key data points involved in business metrics, reports, ML models, and digital operations.
Presented projects and research findings to the wider team.
Data Scientist
MediaWorks
As the sole Data Scientist, I elevated the digital radio data from its raw and nascent state to a mature and analytics-ready asset. I pioneered the end-to-end development of scalable data pipelines, implementing methodical transformations to deploy machine learning (ML) models and stakeholder reports. With the large volumes and varieties of data, I developed ML models such as user activity and churn modelling using Python and Snowflake to guide business strategy.
June 2024 - Apr 2025
Pioneered and owned developing, deploying, and optimising big data pipelines for app and website data via Python and Snowflake. This results in a single source of truth for app and website data at a granular scale.
Increased user data quality by 90% using imputation models with Snowflake SQL.
Predicted the #1 song and artist on The Rock 2000 Countdown for 2024 using machine learning.
Fine-tuned a Retrieval-Augmented Generation chatbot model for financial reporting data.
Developed and automated ETL apps that connect to APIs via Python and Snowflake.
Developed bespoke engagement metrics to model listening behaviour more accurately compared to legacy methods.
Guided business strategy by forecasting user activity and churn using machine learning, and presented insights using automated interactive Tableau dashboards.
Modelled the database structure for scalable and compute-optimised reporting, visualisation, and machine learning.
Advise on digital analytics and marketing operations such as information gathering and integrations.
Spearheaded using GitHub and established guidelines within the Business Insights and Analytics team.
Intern Data Scientist
Ströer Labs NZ
Worked on the ad request optimisation project, which aimed to prevent unprofitable traffic from entering auctions, ultimately improving profit margins through cost savings.
November 2023 - February 2024
Created a model that reduced unprofitable advertising traffic down to 50%, reduced opportunity costs by 20%, and increased profits compared to the past model.
Experimented with various categorical encoding methods, machine learning techniques, and solution architectures in Python.
Performed ETL on advertising traffic data through pySpark as preparation for modelling.
Productionised the project by creating Python modules, test files to verify bespoke functions, a docker image to run the entire program, and an Airflow DAG file for scheduling.
Ran the project on a cloud-based machine learning platform.
Part-Time Google Specialist and Digital Analyst
Orba Shoes
Manage the creation, optimisation, and reporting of Google assets.
March 2023 - November 2023
Developed a multi-channel strategy for the brand using localised market research data on key buyer personas.
Audited and managed Google Assets, and optimised towards ad operations and SEO.
Planned, implemented, analysed, and optimised Google Ad operations through historical data analysis and A/B testing.
Migrated and managed Google Analytics properties to Google Analytics 4 by ensuring past data points and analyses were maintained.
Used Python to periodically extract campaign data from Facebook Ads and the eCommerce platform onto cloud storage.
Created a dashboard integrating 5 data sources.
Optimised copy and targeting for Google Ads.
Part-Time Research Assistant
University of Canterbury - Arts Digital Lab
Programmatically gather, analyse, and visualise sentiment on the Taniwha using Natural Language Processing techniques.
August 2023 - November 2023
Extracted text data from online sources using Python.
Used NLP via Python to extract, transform, and prepare text data for analyses.
Used machine learning to group documents and perform sentiment analysis.
Research, collate, and analyse information, and summarise findings in a variety of formats.
Senior Performance Marketing Manager
David & Golyat Management, Inc.
Provided end-to-end marketing consultancy services ranging from market analyses and brand audits to campaign management and optimisation.
September 2021 - January 2023
Conduct media planning using quantitative market analysis tools and brand audits to cover all stages of the consumer journey.
Manage and optimize Paid Search, Facebook, and Programmatic (Google) campaigns from end-to-end.
Reduced App Install costs by 30% and increased Programmatic clickthrough by 4x.
Implement improvements to planning, implementation, analyses, and optimization processes in the organization.
Reduced lead generation acquisition costs by 44% in 2 months through systematic audience segmentation, A/B Testing, and significance testing in RStudio.
Increased eCommerce Return on Ad Spend by 4.5x on Facebook Ads through consumer segmentation and increased Programmatic clickthrough by 9x by optimizing customer touchpoints.
Use Web Scraping to create sentiment analyses to provide insights to the creative direction.
Use Google Analytics to create comprehensive analyses on consumer profiles, acquisition channels, and website behavior leading to efficient follow-through campaigns.
Use Google Query Language to automate the weekly reporting process, reducing completion time by 60%.
Digital Project Manager
Viventis Search Asia
End-to-end management of recruitment marketing campaigns and change management towards the use of the Hubspot Suite for Marketing.
February 2020 - September 2021
Gained up to 30x return on ad spend (ROAS) for Recruitment Marketing campaigns using Facebook Ads for a Financial Services account with highly specialized roles, and 76x ROAS for an account in the BPO industry.
Handled end-to-end Facebook Ad and Google Ad B2B campaigns — covering setup, optimization, and reporting within a restricted set of KPIs and gained at least 70% sales accepted leads among signups.
Created a business case, implementation plan, and digital marketing strategy for B2B operations, and got executive buy-in.
Created a company-wide lead nurture strategy, lead qualification strategy, content plan, and reports dashboard aimed at accelerating pipeline conversions.
Increased the ease of sales enablement through the creation of training plans, automation, and other digital assets.
Produced creative assets for both Facebook Ads and Programmatic Ad B2B campaigns.
Increased ROAS using Google Tag Manager to set up custom events for remarketing and audience-building.
Reduced 47% of manual B2B marketing operations in 3 months by spearheading the technical setup and integration of the CRM and marketing automation tool.
Created an interactive dashboard using Google Data Studio to combine data from Facebook Ads, Google Analytics, and Google Sheets. Enabled auto-updating using Facebook Graph API and Google Query Language.
Optimized data management using marketing automation workflows to determine contact properties for segmentation, qualification, and sales enablement.
Optimized marketing operations management through KPI creation and reporting by establishing clear data points with the use of marketing automation.
Visualized Google Search Console data through Google Data Studio to identify SEO gaps and content opportunities.
Senior Digital Marketing Specialist
SQREEM Technologies
Managed global campaigns from end-to-end and modelled the data structure for the proprietary Ad Serving tool.
March 2019 - January 2020
Handled Facebook Ad and Programmatic Ad campaigns — covering setup, data-led optimization, and reporting within a restricted set of KPIs.
Doubled a multinational pharmaceutical company's sales, increased website traffic, and increased event attendance. This campaign yielded contracts with the client's 80+ global branches.
Reduced a major banking client's Cost per Acquisition by 90% compared to historical performance.
Produced creative assets for both Facebook Ads and Programmatic Ad campaigns.
Reduced up to 60% of ad operations through automated ad setup by spearheading and modelling the development of the proprietary Ad Serving tool, which mapped data requirements and platform restrictions.
Analyzed gaps in ad operations to be automated and created a business case to demonstrate the projected increase in efficiency.
Worked with developers to create the minimum viable product, its expected functions and workflows.
Interim Creatives Director
SQREEM Technologies
Liased high level creative requirements to the team and contributed domain expertise for the proprietary Ad Creation tool.
February 2019 - December 2019
Liaised, evaluated, and managed creative requirements from the clients to the Digital Creatives Team to meet strict KPIs in the effort to optimize creative performance for the Digital Marketing Team.
Crafted and implemented a training plan for the team.
Troubleshot issues regarding interactive ad production.
Spearheaded developments of the proprietary Digital Creatives tool in the effort to optimize the workflow for both the Digital Marketing Team and Digital Creatives Team.
Digital Marketing Specialist
SQREEM Technologies
Managed global campaigns from end-to-end and designed creative materials.
July 2018 - March 2019
Handled Facebook Ad and Programmatic Ad campaigns — covering setup, data-led optimization, and reporting within a restricted set of KPIs.
Produced creative assets for both Facebook Ads and Programmatic Ad campaigns.
Produced creative studies, workflows, and developments to the company's proprietary creative tool.
Acted as the main guide for Digital Marketing team on the effective use of the proprietary creative tool.
Education
University of Canterbury
Master of Applied Data Science
GPA: 8.58/9
Graduated with Distinction
February 2023 - February 2024
Ateneo de Manila University
Bachelor of Science in Electronics and Communications Engineering
Second Honors (2nd Semester AY2015-2016)
Minor in Japanese Studies
2012 - 2017
Skills
Programming Languages & Tools
Other Programming Tools
Snowflake + SnowPark
SQL / SQLITE
Apache Airflow
Google Cloud Platform APIs
Meta APIs
Commercial Competencies
Project Management
Data Management and Database Design
Digital Advertising and Marketing Consulting
Market Research
Campaign Management
Digital Analyses
Brand Audits
Interests
Besides data science work, I enjoy activities like:
Hiking, going to the gym, and going for a run.: I like staying active, usually through a group fitness activity.
Playing story-driven video games: I like interesting narratives in interactive media as it allows for a creative way to learn more about the world.
Cooking: I cook for both practicality (through meal prep) and enjoyment (through the occasional indulgent treat).
Awards & Certifications
University of Canterbury (Dec 2023): Certificate of Excellence (Master of Applied Data Science)