Master's thesis in Data&AI: Fair and trustworthy recommendat …, Veenendaal

Overview Recommendation systems often favor dominant sellers and ignore user context, leading to biased and irrelevant suggestions. This thesis examines how AI can improve both fairness and trustworthiness in e-commerce recommendations. You’ll analyze existing methods, test algorithms on real‑world data, and design a solution that balances market visibility with user relevance.

Assignment The aim of this thesis is to contribute to the development of fair and trustworthy recommendation algorithms for e‑commerce platforms using AI. This assignment addresses both fairness and reliability through three main stages:

Literature Review and Analysis

– Explore existing research on bias in recommendation systems, identify fairness metrics, review mitigation approaches, and study methods for incorporating user feedback.

Algorithmic Evaluation

– Compare algorithms that explicitly optimise fairness using publicly available datasets (e.g., Amazon Reviews, MovieLens), evaluating performance in terms of recommendation quality, fairness, and diversity.

Solution Design

– Develop an approach that combines fairness and trustworthiness, improving usability of e‑commerce recommendations. Measure impact using clearly defined metrics, possibly via a prototype webshop.

This thesis should contribute to academic discourse on fairness in AI while offering practical insights for improving recommendation systems in online commerce.

Requirements B2 language proficiency in Dutch is required.

#J-18808-Ljbffr