30 March 2021 In this second article of the series of two, I will dive into the deployment and the serving of our models at scale.
25 March 2021 How we handled the training and the deployment of our FastAI models using AI Platform — Part I
23 February 2021 Where data was once used only to measure performance, revenue goals and conversion rates, today, companies with solid historical data can also use it as input for content creation. Daniel de Vos, Manager Data & Analytics at Artefact Netherlands explains how.
5 February 2021 In this article, Data Scientist Maxime Lutel sums up his learnings from the M5 sales forecasting competition, which consisted in predicting future sales in several Walmart stores. He will walk you through our solution and discuss what machine learning model worked the best for this task.
25 January 2021 By definition, search is one of the major levers of digital marketing. In this article, Vincent Laquerriere, Account Executive at Artefact, explains how to optimise your Google positioning strategy to stay ahead of your competitors, and how to maximise your use of Google campaign management tools by integrating data that’s important to your company.
7 January 2021 To see real returns on AI and Machine Learning investments, business leaders first need to understand the cause-and-effect relationships impacting performance. Siddharth Mohan, Senior Data Scientist at Artefact Netherlands & France, explains how Causal Intelligence can boost performance.
25 November 2020 In this article, Artefact’s Senior Data Scientists Kasra Mansouri and Camille Le Gonidec explain how to create a data science product with limited data and high business constraints. Find out how they were able to reduce product stock outs in hypermarkets with Time Series modelling.
25 November 2020 In this article, Amale El Hamri, Senior Data Scientist at Artefact France explains how to train a language model without having understanding the language yourself. The article includes tips on where to get training data from, how much data you need, how to preprocess your data and how to find an architecture and a set of hyperparameters that best suit your model.
25 november 2020 At Artefact, we are so French that we have decided to apply Machine Learning to croissants. This first article out of two explains how we have decided to use Catboost to predict the sales of “viennoiseries”. The most important features driving sales were the last weekly sales, whether the product is in promotion or not and its price. We will present to you some nice feature engineering including cannibalisation and why you sometimes need to update your target variable.
Understanding NLU benchmarks for intent detection and named-entity recognition in call centre conversations
25 November 2020 Call centers advisors are starting to see NLU emerging in their day to day lives, helping them answering customers’ requests more easily. For a tool to do that, it must be able to recognize at the same time the customer request and its characteristics, in other words, an intent and named-entities.