Mejorar el comercio electrónico en la moda: modelos para predecir y algoritmos para aumentar las ventas

Objective: This study analyzes how predictive models and AI algorithms influence fashion electronic trade optimization, assessing their impact on personalizing the user experience and increasing sales. Materials and methods: A quantitative approach with a non-experimental, cross-sectional, and correlational design was used, applying surveys to 50 fashion retail companies with an online presence, and to 500 consumers active on electronic trade platforms. Data were collected through surveys and databases, analyzing factors such as the implementation of artificial intelligence, the conversion rate, and the customer loyalty. For the analysis, descriptive and inferential statistics tests, including correlation and regression analysis, were used for the analysis. Results: The results evidence that AI has a significant impact on sales and customer loyalty, with a positive correlation (r = 0.87; p < 0.001) between AI-based personalization and loyalty of the user. Furthermore, companies with the highest use of AI were found to achieve a conversion rate of 9.8%, while those with the lowest use achieved only 3.2%. Regression analysis indicates that predictive models used in product recommendation strategies significantly improved sales, highlighting the importance of automation in consumer decision-making. Conclusions: It is concluded that AI is a key advantage in fashion electronic trade, enabling a more personalized and effective experience. The implementation of predictive models and machine learning algorithms not only optimizes sales but also strengthens the relationship between brands and their customers.