Haarlem, North Holland, Netherlands
My posts & comments reflect my own opinions. I'm a data scientist, bridging the gap between data engineering and the product/business side. Expertise: attribution, CPC bidding, visitor/customer analytics, large-scale data processing, online performance marketing, social science research methodologies. Tech: - Python, R, bash, SQL - Apache Spark, Hive, Oozie, HDFS, BigQuery, DataProc, MySQL, Snowflake, dbt - grafana, git, AI coding assistants I'm good at: - Designing data pipelines, ETL tasks in data lakes which are fast, reliable, and getting cheaper. - Applying statistical models to uncover insights with testable value potential - Effectively managing stakeholders, prioritizing projects, delivering solutions. - Building CPC bidding algorithms to automate efficient performance marketing at scale with measurable impact on the bottom line - Designing and analysing randomised controlled trials, A/B tests - Analysing causality on observational data. - Optimising big data jobs to reduce compute and storage costs while maintaining performance - Automating analytical processes from notebook to workflow - Connecting data from disparate systems (both conceptually and operationally) - Finding meaningful solutions business problems when data is in play. I have a background in sociology with a focus on quantitative methods in social sciences, survey statistics, organisational behaviour and sociology of management.
Data and Analytics Engineering on multi-touch attribution products delivering positive bottom line impact. - Full ownership of the majority of multi-touch attribution data pipelines - Data architecture design for new use cases - Customer and product insights / experiment design - Developing fine-grained monitoring, observability and alerting capabilities - Placing data quality as a first class citizen - Onboarding new data scientists and data engineers - Optimising large scale Apache Spark jobs - Cloud migration - Temporary (2x 6 months) assignments to support teams with analytics engineering and product insights Tech: - Python, Apache Spark, Apache Hive, Apache Oozie, Hadoop, graphite, Grafana, git, bash, dbt, Snowflake
Established multi-touch attribution capabilities for performance marketing use cases. - Part of the first team working on multi-touch attribution for marketing. - Scoping business problems (valuation of marketing channels) and solving with scalable data products. - Aligned data production and consumption requirements with stakeholders across the business - Developed distributed data pipelines to extract and transform hundreds of GB of visitor data per day - Applied attribution models to visitor data to fairly distribute conversions across marketing channels - Supported decision making and product development with exploratory data analysis and insights - Designed experiments to test competing attribution models - Developed and optimised large-scale Hadoop jobs in Apache Hive and Apache Spark - Used Apache Oozie for workflow orchestration Tech: - Apache Spark, Apache Hive, MySQL, bash scripting, Hadoop streaming, HDFS, Google Analytics, BigQuery, Google Cloud Storage
Developed CPC bidding algorithms for travel metasearch campaigns. - Built CPC bidding solutions to maximise conversions with ROI constraints on performance marketing channels - Tens of millions of bids submitted daily - Developed bidding algorithms based on statistical models and business rules - Built data pipelines to fully automate the above - Communicated with external stakeholders/partners on performance, technical integration and new bidding features - Performed data analysis / reporting / presentations for internal stakeholders - Participated in the recruitment of future high performers
Supported the development and design of a centralised marketing/CRM database. - Collaborated closely with vendors and internal stakeholders to achieve a single customer view in a 3rd party CRM/marketing automation solution. - Established workflows around a newly acquired email marketing orchestration solution - Communicated/aligned our requirements with software vendors - Performed ad hoc analysis for business stakeholders - Automated legacy data processes
Generalist on the agency side of market research: client relations / project coordination / data analysis. - Maintained productive relationships with FMCG/retail clients - Wrote proposals for market research tenders - Coordinated research projects across field and data processing divisions - Guided a team of in-store retail auditors to maintain objectivity and data quality - Performed data analysis, reporting and report design using MS Excel, MS Access and SPSS - Automated recurring analytical processes using VBA programming and SPSS Types of projects: - Longitudinal brand tracking - Mystery Shopping - Retail audit - Price sensitivity studies Research Methods: - Explorative Data Analysis - Conjoint Analysis - Correspondence Analysis - Van Westendorp method
Generalist in PR and online marketing - Managed PPC campaigns on Google AdWords and Facebook - Wrote press releases, blog posts, advertising copies - Liaised with representatives of publications/magazines - Prepared proposals for marketing communications tenders - Built WordPress websites - Developed website content with brand messaging and SEO in mind - Localized website content and brand/advertising assets
Assisted in quantitative, survey-based consumer research projects for major FMCG/retail clients. - Data visualisation for market research reports - Exploratory statistical analysis - Client communication - Data quality checks - Translation of reports, questionnaires