Modulai has together with Lindex developed and deployed a custom built recommender system. Lindex is dedicated to offer the customers a relevant and transparent personalized experience, in a multi-channel context. To be able to deliver on that ambition, a robust recommender system is considered a vital cornerstone.
Data on approximately 60000 products and purchases from over 2 million customers was used. Customers were characterized using their historical transactions. Various sets of data were considered for feature extraction, including multiple levels of product categories, product attributes such as color, texture and material. Natural language data was included and processed using various classical NLP techniques, Universal Sentence Encoders, FastText and BERT. Image data was transformed into dense representations using ResNet and convolutional autoencoders to be included in the modeling. Recommendations were produced on an individual level using both matrix factorization and gradient boosting models.
Lindex is a major retailer, active in the nordics and throughout Europe. Lindex has several million registered customers, and is one of the prominent brands in womens’ wear, lingerie and kids wear.
How Modulai did it
Preprocessing, training, validation and inference flows were developed in Python on Azure. Primary tools/environments for the project were Snowflake, Databricks and Spark with orchestration through Apache Airflow. Model training was performed using various open-source libraries. Product text was utilized to provide even better recommendations, with feature extractors developed in TensorFlow.