Richard F.

Design and deployment of a data-driven nutrition web application, with generation of personalized plans based on user inputs.

Implementation of end-to-end data pipelines (onboarding → plan generation → performance tracking), with workflow automation.

Development of backend logic and transformation of data into concrete, actionable recommendations.

API integration, database structuring, and real-time update management.

Implementation of feedback loops to continuously improve the quality of recommendations.

End-to-end product management (design, data architecture, business logic, UX).

Pioneered the group's data practice as the first data hire, collaborating across multiple teams to drive internal process optimization, develop automation tools, and implement robust statistical analysis. This cross-functional effort improved data processing speed by 30% and enhanced data accuracy by 10%, directly supporting strategic business outcomes

Led the end-to-end delivery of 5 data-driven strategy projects, facilitating discussions to translate client requirements into tailored data solutions aligned with business goals, and effectively communicating technical concepts in a clear, strategic manner, which allowed growth in both client satisfaction and retention

Enhanced team efficiency by decreasing number of hours on data processing by 30% through the creation of 20 automation projects using Python and VBA, optimizing ETL (Extract Transform Load) processes and workflows internally

Increased prediction accuracy by 15% for key business metrics such as brand advocacy and product usage through the design and deployment of predictive models for classification and regression tasks using Python, leveraging advanced techniques like dimensionality reduction and predictive modeling to align BAV proprietary metrics with clients' critical KPIs

Led a research to predict respondents' personality based on their eye movement, using my knowledge in coding and Psychology. The analysis required analyzing images and the eye position, latency on specific areas and motion for the different types of images and resulted in my Research paper being certified by NYU

Conducted the Data Analysis to predict implicit attitude changes from four main sets of variables, including demographics and exposure to media, using logistic and non-linear regression. I was able to reach statistical significance in predicting attitudinal changes following US Supreme Court rulings with an accuracy of 90%