Inditex, headquartered in Arteixo, Spain, stands as one of the world's largest and most influential fashion retailers. Founded in 1985, Inditex has rapidly expanded, boasting a portfolio of renowned brands like Zara, Pull&Bear, Massimo Dutti, and Bershka. It's unique, fashion model, grounded in a robust supply chain and nimble production capabilities, has redefined the fashion industry. With a commitment to sustainability, Inditex has set ambitious goals to reduce its environmental footprint and promote ethical practices across its vast network of stores and suppliers. As a global leader in the fashion retail sector, Inditex continues to shape trends and provide affordable, stylish clothing to customers worldwide, all while embracing responsible and innovative business practices.
At Inditex, the Data Science and AI team drives innovation by harnessing the power of advanced analytics and artificial intelligence to enhance decision-making across the business. The team analyzes large-scale datasets to uncover patterns, predict trends, and optimize key processes. Using cutting-edge machine learning and AI techniques, the team develops algorithms to solve complex challenges. Collaboration with cross-functional teams ensures our solutions are tailored to real-world needs. The team's goal is to seamlessly integrate data and AI into every aspect of the business, delivering impactful insights and driving sustainable growth.
Understanding causal relationships in retail is essential for making strategic decisions. For instance, introducing a new product can lead to cannibalization, where the sales of existing products decline, or adjusting the price of a product might alter its demand and impact market dynamics. However, these effects often remain obscured by complex interactions between variables and temporal patterns, making it challenging to identify their true causes and predict their outcomes accurately.
This project focuses on developing advanced artificial intelligence (AI) algorithms to explicitly establish causal relationships between such events. Using state-of-the-art techniques in causal inference and deep learning, we aim to uncover the hidden connections between retail actions (e.g., product launches, price changes) and their effects on sales and demand.
Our goal is to build predictive models that not only estimate these impacts but also provide actionable insights by simulating counterfactual scenarios, helping businesses plan better. Additionally, we will design tailored Key Performance Indicators (KPIs) to quantify critical dynamics like cannibalization and price elasticity of demand, ensuring retail decision-makers have practical tools for evaluating their strategies. This project seeks to provide a scalable, data-driven framework to optimize inventory management, pricing strategies, and overall revenue performance.
From June 9 to August 31, 2025 (adjustable at the discretion of the organisation)