Global Blog
Get inspired by our latest blog articles.
The road ahead: data-driven marketing is critical for the evolving car industry
To the casual observer, the motor industry might seem in good health, with electric and hybrid vehicles increasingly appearing on our streets and driverless cars becoming a reality, not to mention people preferring the safety of their car over public transport following the coronavirus pandemic.
But this surface view belies an industry in flux, facing change from several directions.
2 November 2021
How to secure your Python software supply chain
A guide to being aware of the risks you are exposed to and a few tips to protect against them.
29 October 2021
Ad sequencing: how to generate storytelling on YouTube
Nowadays, advertising saturation on all channels causes the message we want to transmit to be too repetitive and does not inspire interest for the user. In this sense, the option of generating coherent Storytelling for the user can be a complicated task.
If we have a brief where video actions and storytelling are proposed, I think that the YouTube Ad sequence could be an option to value.
Using this type of strategy, we have seen increases in frequency up to 2.4x and Brand Awareness up to 4x through YouTube Brand lift measurements.
28 October 2021
7 pandemic-driven business lessons learned for the long-term
For over a year and a half, organizations have undertaken a continuous cycle of innovation and adaptation to meet the changing environment as the pandemic continues to play out. Ghadi Hobeika, CEO of Artefact in the US, provides an overview of seven learnings from the pandemic for the long-term.
27 October 2021
Serving ML models at scale using Mlflow on Kubernetes – Part 3
This article is the third part of a series in which we go through the process of logging models using Mlflow, serving them on Kubernetes engine and finally scaling them up according to our application needs. Although this article could be used independently to test any API response, we recommend reading our two previous articles (part1 and part2) on how to deploy a tracking instance and serve a model as an API with Mlflow. In the following, we will be interested in the scalability issue and address it with few experiments to understand k8s cluster behavior and give recommendations on how to handle high loads.
26 October 2021
Serving ML models at scale using Mlflow on Kubernetes – Part 2
25 October 2021 This article is the second part of a series in which we go through the process of logging models using Mlflow, serving them as an API endpoint, and finally scaling them up according to our application needs. We encourage you to read our previous article in which we show how to deploy a tracking instance on k8s and check the hands-on prerequisites (secrets, environment variables…) as we will continue to build upon them here. In the following, we show how to serve a machine learning model that is already registered in Mlflow and expose it as an API endpoint on k8s.
25 October 2021
Serving ML models at scale using Mlflow on Kubernetes – Part 1
22 October 2021 MLflow is a commonly used tool for machine learning experiments tracking, models versioning, and serving. In our first article of the series “Serving ML models at scale”, we explain how to deploy the tracking instance on Kubernetes and use it to log experiments and store models.
22 October 2021
Visual time series forecasting with Streamlit Prophet
22 september 2021 You need a baseline for your latest time series forecasting project? You want to explain the decision-making process of a predictive model to a business audience? You would like to understand if car prices are seasonal before buying a new one? We might have something for you! This article introduces Streamlit Prophet, a web app to help data scientists train, evaluate and optimize forecasting models in a visual way. Forecasts are made with Prophet, a fast and easily interpretable model.
22 September 2021
The path to developing a high-performance demand forecasting model — Part 3
10 september 2021 How to choose the right visualizations and implement them in Streamlit to better debug your forecasting models
10 September 2021
Demand forecasting: Using machine learning to predict retail sales
24 August 2021 All industries aim to manufacture just the right number of products at the right time, but for retailers this issue is particularly critical as they also need to manage perishable inventory efficiently
24 August 2021
The $2 Trillion Club: how Data x Services are leading to skyrocketing growth in company valuations
5 August 2021 Recently, Microsoft joined Apple as the second listed US company (and third in the world, alongside Saudi oil giant Aramco) as a member of the very select $2 trillion club. The fact that US tech giants are dominating the world is not news, but the pace at which they’re crossing significant valuation milestones is. It took less than 18 months for them to move up from $1 trillion to $2 trillion. How is this even possible? What can “legacy” companies take away from this unparalleled economic success?
5 August 2021
AI Requires a Holistic Framework and Scalable Projects
28 July 2021 Artificial intelligence and digital transformation projects have a low success rate, but best practices help.
28 July 2021
Including ethics best practices in your Data Science project from day one
27 July 2021 Here are some guidelines to build trustworthy machine learning solutions without falling into ethical pitfalls.
27 July 2021
Walkthrough Amazon’s new attribution tool (still in beta)
11 July 2021 A really promising tool for manufacturers with a strong Amazon product presence that aims at improving media performance and increasing revenue through holistic ROI measurement.
12 July 2021
From marketing personas to media activation: from theory to reality, reconciliation can’t be improvised
7 July 2021 Reconciliation between theory and reality, or between persona types and their effective targeting via media activation tools such as Google Ads or Facebook Ads, can pose serious issues and lead to a loss of media investment profitability.
7 July 2021
5 good reasons to use SA360 for SEA campaigns in 2021
1 July 2021 SEA management has changed a lot in the last few years, evolving from time-consuming manual to increasingly automated. Many tools have been marketed to improve and accelerate account management.
6 July 2021
How to deploy and secure your Streamlit app on GCP?
28 June 2021 Streamlit is a great tool to create beautiful data applications quite easily but when it comes to deploying them and making them accessible, it can be more complicated for non-specialists. In this article we aim at presenting our journey to deploying our application on GCP ensuring a restricted access to specific people. We implemented two solutions: one with Cloud Run, the other with App Engine and we chose to keep App Engine for its ease of securing the application with IAP (Identity-Aware Proxy).
28 June 2021
Retailers: it’s time to enter the Unified Commerce era
22 June 2021 Shopping for gifts is a struggle for me. Especially when it comes to gifting my mom. A couple of weeks ago, I was looking for some ideas for her birthday. As usual, I was late and as usual, I was pretty uninspired.
22 June 2021
Data-driven marketing: the rise of the customer data platform
21 June 2021 Data-Driven Marketing | This seems the perfect moment for the widespread adoption of Customer Data Platforms or CDPs.
22 June 2021
Think with Google article | Google Talk Series at Vivatechnology 2021 – Data intelligence: turning data into value
21 June 2021 The potential for transforming data into value through product, service or process innovation is immense, and companies that succeed in doing so outperform their competitors. Yet, only 30% of data-driven transformation projects achieve their objectives, often stumbling on scaling up.
21 June 2021
Applying machine learning algorithms to satellite imagery for agriculture applications
14 June 2021 A step-by-step guide on how to detect, outline and classify farm plots on satellite images. This article is part of a 2-article series about satellite images processing applied to agriculture.
14 June 2021
Powering your call centre with artificial intelligence
3 June 2021 Learn how to improve customer satisfaction and create added-value using Google Contact Center AI. Read about the key outcomes of the webinar on March 30th presented by Matthieu Myszak - Data Consulting Director, Artefact and Julien Tribout - Sales Lead Google Contact Center AI.
3 June 2021
The path to developing a high-performance demand forecasting model — Part 2
27 May 2021 In this following article of a large series of posts dedicated to demand forecasting, we will focus on how to model promotions, a key driver in sales forecasting, looking at what a typical promo dataset looks like, how features should be crafted, with a step-by-step example in Python, and how complex promotional granularity can be dealt with.
27 May 2021
Intelligent sales: preparing for the imminent sales revolution
24 May 2021 Fabien Cros, Data Consulting Director, Artefact, describes a seamless world where a sales team can operate via a centralised sales command centre (SCC), and more importantly, how this world is adaptable now.
25 May 2021
Google keeps innovating: Responsive Search Ads are now the standard advertising type
17 May 2021 Google keeps innovating: Responsive Search Ads are now the standard advertising type
18 May 2021
The untapped wealth of WeChat data for brands
11 May 2021 Brands are not fully realising the opportunity of both capturing and actioning on WeChat's many data touchpoints, with much data sitting unused in third-party systems. The data and consulting director at Artefact advises how to unlock WeChat's data dam.
11 May 2021
Leveraging satellite imagery for machine learning computer vision applications
5 May 2021 A step by step guide on how to collect and preprocess satellite imagery data for machine learning algorithms
5 May 2021
Why paid search practitioners must embrace automation
21 April 2021 Innovations such as Auto Applied Recommendations and even the changes in match types are taking control away from the PPC practitioner and into the black box. But rather than fear the worst, we should embrace automation, says Tristan Sanders, Head of Performance at Artefact UK.
25 April 2021
Conditions required for successful AI-driven digital transformation
19 April 2021 Artificial Intelligence (AI) is increasingly becoming part of everyday language of businesses as they look for better, quicker and smarter ways to run. But despite the promise it offers, the majority of initiatives will not deliver business outcomes.
15 April 2021
What is the single most transformative digital marketing trend of the last few years?
16 April 2021 Tristan Sanders, Head of Performance at Artefact UK, puts the case forward for the deeper interrogation of audiences, enabled by the proprietary tech they’ve built on top of Google BigQuery.
15 April 2021
1st party data: Taking control in the cookie-less marketing era
As we step into the cookie-less marketing era come 2022, the rules of marketing will evolve and it is imminent for marketers to adapt their ways of marketing operations.
15 April 2021
The path to developing a high-performance demand forecasting model — Part 1
14 April 2021 Demand forecasting is always challenging, we all know that. In this series of articles you will understand the main challenges of developing a complex forecasting model on a real world problem.
14 April 2021
Serving FastAI models with Google Cloud AI Platform
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.
30 March 2021
Automating the training of ML models with Google Cloud AI Platform
25 March 2021 How we handled the training and the deployment of our FastAI models using AI Platform — Part I
25 March 2021
When data creates a monster, it’s time for bravery
24 March 2021 When a business comes to depend on the data silos that are hurting it, it’s time for brave leadership and a comprehensive strategy for data, writes Hannes Weissensteiner, Managing Director DACH at Artefact.
24 March 2021
Second-party data partnerships: when your basic data is gold for someone else
16 March 2021 The concept of data monetisation has been used everywhere and by everyone… But other than the GAFA, very few companies have successfully monetised their data and created a real income stream from it. Of course, data has been a key driver for the most recent business successes, but it seems that the big promises of data monetisation never really bore fruit for most. That’s because most companies didn’t yet explore second-party data partnerships, says Fabien Cros, Data Consulting Director at Artefact France.
18 March 2021
How far are we from delivering truly personalised advertising at scale?
26 February 2021 While audiences are becoming increasingly receptive to personalised advertising, many are still sceptical of its execution and implementation. So, how far are we from delivering truly personalised advertising at scale? Tristan Sanders, Head of Performance Marketing at Artefact, considers how advertisers can move forward.
12 March 2021
Data Analysts: Feeding creatives with contextual Data
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.
12 March 2021
Boosting online retail activity by upskilling sales and marketing teams.
23 February 2021 Ecommerce is more than an opportunity for brands: it’s a necessity, say Thomas Faure, Senior Consulting Manager – E-Retail Lead and Guillaume BAROIN, e-Retail Consultant at Artefact. They explain how upskilling programmes can accelerate overall business growth.
12 March 2021
Interview: How Nissan is transforming in the digital world
17 February 2021 In this Q+A, Dév Rishi Sahani, Nissan’s Global Head of Customer Experience Data Analytics & Reporting, chats with Pascal Coggia, Artefact Partner and UK Managing Director, to explain how the Japanese car giant has accelerated its digital transformation over the last few years and is now using data and BI Hubs to drive operational efficiencies and sales around the world.
12 March 2021
The real impact of the iOS 14 update on Facebook Advertising (and how advertisers should respond)
10 February 2021 Many articles have been written about Apple’s latest iOS 14 update, and the ad restrictions it introduces. Arnaud Marro, Head of Social Media at Artefact, and Cecile Megens, Sr. Paid Media Consultant, analyse the impact on marketing performance and explain how advertisers can respond.
12 March 2021
Why linking Adjust and Google Cloud Platform can improve data-based marketing strategies
8 February 2021 Collecting user data is easy. However, understanding how to maximise value and respond to real-time behaviour changes is far more challenging. Jenson Jacob, Data & Analytics Manager at Artefact MENA explains why linking Adjust and Google Cloud Platform can improve data-based marketing strategies.
8 March 2021
Sales forecasting in retail: what we learned from the M5 competition
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.
8 March 2021
Using NLP to extract quick and valuable insights from your customers’ reviews
3 March 2021 Everyone talks about BERT, GPT-3, XLNet… but did you know that with some simple NLP 101 preprocessing you can already extract valuable insights from your data?
3 March 2021
Introducing NLPretext, a unified framework to facilitate text preprocessing.
23 February 2021 Working on NLP projects? Tired of always looking for the same silly preprocessing functions on the web, such as removing accents from French posts? Tired of spending hours on Regex to efficiently extract email addresses from a corpus? Amale El Hamri will show you how NLPretext got you covered!
22 February 2021
From idea to implementation: Becoming an AI Factory
29 January 2021 Formulating a coherent AI strategy, and deploying value-adding and efficient use cases is a struggle for many businesses. Alexandre Thion de la Chaume, Partner, Data Consulting at Artefact, explains how these processes can be streamlined through the AI Factory model.
29 January 2021
How can data enhance search strategies and boost ROI?
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.
25 January 2021
How did we use computer vision to help medical experts diagnose Follicular Lymphoma?
25 January 2021 With the introduction of opt-in permissions for apps, iOS 14 will make it harder for brands to target consumers on an individual level and to measure results of marketing activities. Bobby Gray, Head of Analytics and Data Marketing at Artefact, considers the impact and explains how brands can respond using first-party data.
25 January 2021
Welcome to the Google Analytics 4 revolution
21 January 2020 To implement GA4 successfully, companies first need to implement a dual setup with their current Universal Analytics property and upskill their digital marketing teams accordingly. Cyril Calvet, Senior Data Analyst at Artefact France, explains how.
21 January 2021
Cracking personalisation in China.
20 January 2021 Chinese users spend 4.7 hours a day or more on their smartphones, generating massive amounts of data. Xavier Mussard explains how segmentations capturing personas, life stage, and engagement can offer personalisation in the world’s largest internet market.
20 January 2021
Causal Intelligence: The Key to boosting AI Performance in Business
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.
7 January 2021
How to master the basics of people-based media attribution
5 January 2021 Marketing attribution tools, like Facebook Attribution, Google Analytics and Adobe Analytics can help marketers gain unique insights into what their consumers are doing across channels and touchpoints — but only if they set them up correctly. Katharina Zilke, Head of Social Media at Artefact Germany, outlines the five steps marketers can take to give themselves the best chances of success.
5 January 2021
How Apple’s iOS 14 will change how brands target consumers
14 December 2020 With the introduction of opt-in permissions for apps, iOS 14 will make it harder for brands to target consumers on an individual level and to measure results of marketing activities. Bobby Gray, Head of Analytics and Data Marketing at Artefact, considers the impact and explains how brands can respond using first-party data.
14 December 2020
The time is now for people-based attribution
25 November 2020 Marketers have longed to be able to track when, where and how their consumers are interacting with their brands — online and offline. Tools like Facebook Attribution can help brands take a critical step forward in their understanding, says Arnaud Marro, Head of Social Media at Artefact France.
25 November 2020
Reducing product stock-outs in hypermarkets with Time Series modelling
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
How to train a language model from scratch without any linguistic knowledge
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
How did we put our sales forecasting solution for croissants into production?
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.
25 November 2020
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.
24 November 2020
Interview: Helping HomeServe better respond to home emergencies with AI
24 November 2020 This October, Artefact hosted a webinar with home insurance company HomeServe to discuss how speech analytics is helping the company improve its customer experience and boost business performance. In these extracts, Mickael Loreau, Innovation and Products Director at HomeServe, chats with Artefact Data Consulting Director Matthieu Myszak and Hanan Ouazan, Director – Data Science VP, about the progress they have made so far.
23 November 2020
Why brands need to build more diverse social media strategies
29 October 2020 This summer, big brands boycotted Facebook over allegations it was profiting from hate speech — putting many smaller brands under pressure to follow suit. To avoid such difficult decisions in future, smaller brands should start building more diverse social media strategies says Jack Harrington, Paid Social Manager at Artefact UK.
28 October 2020
