Artefact Research Center

Bridging the gap between academia and industry applications.

Research on more transparent and ethical models to nurture AI business adoption.

ARTEFACT RESEARCH CENTER

Examples of AI biases

  • AppleCard grants mortgages based on racist criteria
  • Lensa AI sexualizes selfies of women
  • Racist Facebook Image Classification With afro-american as monkeys
  • Microsoft Twitter chatbot becoming nazi, sexist and aggressive
  • ChatGPT that writes a code stating good scientist are white males

Current challenge

AI models are accurate and easy to deploy in many use cases, but remain uncontrollable due to black boxes & ethical issues.

The Artefact Research Center’s mission.

A complete ecosystem that bridges the gap between
fundamental research and tangible industrial applications.

The Artefact Research Center's mission.
Emmanuel MALHERBE

Emmanuel MALHERBE

Head of Research

Research Field: Deep Learning, Machine Learning

Starting with a PhD on NLP models adapted to e-recruitment, Emmanuel has always sought an efficient balance between pure research and impactful applications. His research experience includes 5G time series forecasting for Huawei Technologies and computer vision models for hairdressing and makeup customers at l’Oréal. Prior to joining Artefact, he worked in Shanghai as the head of AI research for L’Oréal Asia. Today, his position at Artefact is a perfect opportunity and an ideal environment to bridge the gap between academia and industry, and to foster his real-world research while impacting industrial applications.

A full ecosystem bridging the gap between fundamental research and industry tangible applications.

A full ecosystem bridging the gap between fundamental research and industry tangible applications.

Transversal Research Fields

With our unique positioning, we aim at addressing general challenges of AI, would it be on statistical modelling or management research.
Those questions are transversal to all our subjects and nurture our research.

Control & accountability

Control &
accountability

  • Controllable Models with guarantees on predictions
  • Interface with Demand planners
  • Category Managers
  • Decision by best model input: enforce reliable prediction even out of train set
  • E.g.: Enforce monotony on input variables
Explainability & transparency

Explainability
& transparency

  • Interpretation of predictions
  • Interface and visualization for non-technical users
  • Adapt the models modules and components to métiers
  • Visualization on understandable inputs, before feature engineering
Bias & uncertainty

Bias &
uncertainty

  • Enrich prediction for better decisions
  • Non-symmetric uncertainty (vs Gaussian) needed by clients
  • Adapted to time-series and assortment optimization
Obstacles & accelerators of AI in business

Obstacles & accelerators of AI in business

  • Study of Organisations
  • Top CAC 40 stakeholders and decision takers interviews
  • Impact of AI ethics, fairness, interpretability
  • Governance, standards and regulations for AI applications

Subjects

We work on several PhD topics at the intersection of industrial use cases and state-of-the-art limitations.
For each subject, we work in collaboration with university professors and have access to industrial data that allows us to address the major research areas in a given real-world scenario.

1 — Forecasting & pricing

Model time series as a whole with a controllable, multivariate forecasting model. Such modelling will allow us to address the pricing and promotion planning by finding the optimal parameters that increase sales forecast. With such a holistic approach, we aim at capturing cannibalization and complementarity between products. It will enable us to control the forecast with guarantees that predictions are kept consistent.

Mohamed CHTIBA

Mohamed CHTIBA

Research Scientist
on Forecasting and Pricing

Artefact
Université paris 1 Panthéon sorbonne

Research Field

Deep Learning, Optimization, Statistics

Jean-Marc BARDET

Jean-Marc BARDET

Professor

Laboratoire SAMM

Université paris 1 Panthéon sorbonne

Research Field

Stochastic Processes, Statistics, Probability

Joseph RYNKIEWICZ

Joseph RYNKIEWICZ

Associate Professor

Laboratoire SAMM

Université paris 1 Panthéon sorbonne

Research Field

Temporal Series, Neural Networks, Statistics

2 — Explainable and controllable scoring

A widely used family of machine learning models is based on decision trees: random forests, boosting. While their accuracy is often state of the art, such models suffer from a black-box feeling, giving limited control to the user. We aim to increase their explainability and transparency, typically by improving the estimation of SHAP values in the case of unbalanced datasets. We also aim to provide some guarantees for such models, e.g., for out-of-training samples or by enabling better monotonic constraints.

Abdoulaye SAKHO

Abdoulaye SAKHO

Research Scientist on
Tree-Based Models

Artefact
Sorbonne Université

Research Field

Statistics, Explainable AI

Erwan SCORNET

Erwan SCORNET

Professor

Laboratoire LPSM

Sorbonne Université

Research Field

Random forests, Interpretability, Missing values

3 — Assortment optimization

Assortment is a major business problem for retailers that arises when selecting the set of products to be sold in stores. Using large industrial datasets and neural networks, we aim to build more robust and interpretable models that better capture customer choice when faced with an assortment of products. Dealing with cannibalization and complementarities between products, as well as a better understanding of customer clusters, are key to finding a more optimal set of products in a store.

Vincent AURIAU

Vincent AURIAU

Research Scientist on Assortment Optimization

Artefact
Centrale Supélec
Université Paris Saclay

Research Field

Deep learning,
Operational Research

Vincent MOUSSEAU

Vincent MOUSSEAU

Professor

Laboratoire MICS

Centrale Supélec
Université Paris Saclay

Research Field

Preference Learning, Multicriteria Decision Analysis, Operations Research

Antoine DESIR

Antoine DESIR

Associate Professor

Laboratoire TOM

Insead

Research Field

Choice Modelling, Assortment Optimization, Operations Research

Ali AOUAD

Ali AOUAD

Assistant Professor

Management Science and Operations

London Business School

Research Field

Dynamic Matching, Choice Modelling, Assortment and Inventory Optimization, Approximation Algorithm, Operations Research

4 — AI Adoption in businesses

The challenge of better adoption of AI in companies is to improve the AI models on the one hand, and to understand the human and organizational aspects on the other. At the crossroads of qualitative management research and social research, this axis seeks to explore where businesses face difficulties when adopting AI tools. The existing frameworks on innovation adoption are not entirely suitable for machine learning innovations, as there are typical differences with regulation, people training or biases when it comes to AI, and more so with generative AI.

Lara ABDEL HALIM

Lara ABDEL HALIM

Research Scientist on AI Adoption in Businesses

Artefact
École Polytechnique

Research Field

Management research, Innovation

Cécile CHAMARET

Cécile CHAMARET

Professor

Laboratoire CRG

École Polytechnique

Research Field

Innovation, Marketing, Qualitative Social Research

5 — Data-driven sustainability

The project will mobilize qualitative and quantitative research methods and address two key questions: How can companies effectively measure social and environmental sustainability performance? Why do sustainability measures often fail to bring about significant changes in organizational practices?

On the one hand, the project aims to explore data-driven metrics and identify indicators to align organizational procedures with social and environmental sustainability objectives. On the other hand, the project will focus on transforming these sustainability measures into concrete actions within companies.

Oualid Mokhantar

Oualid Mokhantar

Research Scientist on Sustainability

Artefact
ESCP Business School

Research Field

Management Research, Economics

Gorgi KRLEV

Gorgi KRLEV

Associate Professor

Sustainability Department

ESCP Business School

Research Field

Sustainability, Social innovation, Organizations Theory

6 — Bias in computer vision

When a model makes a prediction based on an image, for instance showing a face, it has access to sensitive information, such as the ethnicity, gender or age, that can bias its reasoning. We aim at developing a framework to mathematically measure such bias, and propose methodologies to reduce this bias during the model training. Furthermore, our approach would statistically detect zones of strong bias to explain and understand and control where such models reinforce the bias present in the data.

Veronika SHILOVA

Veronika SHILOVA

Research Scientist on Biases in Computer Vision

Artefact
Université Toulouse 3

Research Field

Deep learning, computer vision, biases

Laurent RISSER

Laurent RISSER

CNRS Research Engineer

Institut Mathématiques de Toulouse

Université Toulouse 3
CNRS

Research Field

Explainable Machine Learning, Image Analysis, Interpretable and Robust AI

Jean-Michel LOUBES

Jean-Michel LOUBES

Professor

Institut Mathématiques de Toulouse

Université Toulouse 3
ANITI

Research Field

Unbiased Learning, Interpretable AI, Optimal Transport and Applications to Statistics, Machine Learning

7 — LLM for information retrieval

One major application of LLMs is when coupled with a corpus of documents, which represent some industrial knowledge or information. In such a case, there is a step of information retrieval, for which LLMs show some limitations, such as the size of the input text, which is too small for indexing documents. Similarly, the hallucination effect can also happen in the final answer, which we aim at detecting using the retrieved document and model uncertainty at inference time.

Hippolyte GISSEROT-BOUKHLEF

Hippolyte GISSEROT-BOUKHLEF

Research Scientist on Large Language Models for Information Retrieval

Artefact
Centrale Supélec
Université Paris Saclay

Research Field

Deep Learning, NLP

Pierre COLOMBO

Pierre COLOMBO

Associate Professor

Laboratoire MICS

Centrale Supélec
Université Paris Saclay

Research Field

Large Language Models, Bias in AI, Models Evaluation

Céline HUDELOT

Céline HUDELOT

Professor

Laboratoire MICS

Centrale Supélec
Université Paris Saclay

Research Field

Knowledge Representation, Semantic interpretation, Neural Networks

Artefact’s part-time researchers

Besides our team dedicated to research, we have several collaborators who spend some time doing scientific research and publishing papers. By working also as consultants inspire them with real-world problems encountered with our clients.

  • Michael Voelske

    Michael Voelske

    Research Field

    Large Language Models applications in Information Retrieval and NLP

    Explainable Models in Machine Learning, Retrieval, and Ranking

    IR for complex, task-based information needs

    Artefact

    Since May 2022, I have been at the helm of the Data Science and Engineering team at Artefact Germany, where I apply my academic background in computer science, with a PhD focused on machine learning and information retrieval, to solving the business problems of Artefact’s clients. My role involves not just leading but also inspiring my team to blend cutting-edge AI research with pragmatic applications. Passionate about making complex AI concepts accessible, I strive to leverage technology for both innovative business solutions and meaningful societal impact.

  • Evan Hurwitz

    Evan Hurwitz

    Research Field

    Reinforcement Learning

    Machine Learning

    Finance and Gaming

    Artefact

    Evan holds a PhD Engineering in artificial intelligence where he applied AI techniques to optimising an actively-managed portfolio utilising multiple trading strategies. He has performed research work in Academia, where he co-authored "Artificial Intelligence and Economic Theory: Skynet in the Market". He later moved on to work on green energy solutions using reinforcement learning for S&P Platts, after which he worked with Preqin on ingesting and understanding alternative investment data. He joined Artefact in 2020, and has worked across multiple industries such as Retail, cybersecurity, SaaS, Engineering, Education and real estate, with clients ranging from SMEs all the way to FTSE100 companies.

  • George Cevora

    George Cevora

    Research Field

    Neuroscience

    Deep learning

    Machine learning

    Artefact

    George received his Ph.D. in Theoretical Neuroscience from the University of Cambridge for his work on the mathematical modeling of animal learning. George has 10 years of research experience in deep learning, which he is now applying in industrial settings. Since leaving academia, George has worked across a wide range of industries and problem domains, from jet engines to antibiotic resistance. George has also spent a few years in the area of national security, building a product to combat discrimination resulting from the inappropriate use of AI. Learn more at www.cevora.xyz

  • Savio Rozario

    Savio Rozario

    Research Field

    Machine learning

    Non-linear optimization

    Physics

    Artefact

    Savio holds a Ph.D. in experimental laser plasma physics from Imperial College London, where he used machine learning methods to optimize the experimental configuration of highly nonlinear plasma accelerator systems. He worked at EY in their tax R&D department, developing machine learning solutions for compliance monitoring across multiple geographies using large language models. He joined Artefact in 2022 and has delivered end-to-end data science solutions across a variety of sectors including retail, transport and real estate for FTSE250 organizations.

  • Nelson Peace

    Nelson Peace

    Artefact

    Nelson spent the first decade of his career in a combination of equity and commodity markets, where he deployed quantitative trading strategies in OTC markets. After completing his MSc in Data Science in 2021, he joined Artefact’s UK office as a data scientist, where he works on data science problems across a range of domains, with expertise in AI applications in financial markets and trading.

Publications

Medium blog articles by our tech experts.

The era of generative AI: What’s changing

The era of generative AI: What’s changing

The abundance and diversity of responses to ChatGPT and other generative AIs, whether skeptical or enthusiastic, demonstrate the changes they're bringing about and the impact...

How Artefact managed to develop a fair yet simple career system for software engineers

How Artefact managed to develop a fair yet simple career system for software engineers

In today’s dynamic and ever-evolving tech industry, a career track can often feel like a winding path through a dense forest of opportunities. With rapid...

Why you need LLMOps

Why you need LLMOps

This article introduces LLMOps, a specialised branch merging DevOps and MLOps for managing the challenges posed by Large Language Models (LLMs)...

Unleashing the Power of LangChain Expression Language (LCEL): from proof of concept to production

Unleashing the Power of LangChain Expression Language (LCEL): from proof of concept to production

LangChain has become one of the most used Python library to interact with LLMs in less than a year, but LangChain was mostly a library...

How we handled profile ID reconciliation using Treasure Data Unification and SQL

How we handled profile ID reconciliation using Treasure Data Unification and SQL

In this article we explain the challenges of ID reconciliation and demonstrate our approach to create a unified profile ID in Customer Data Platform, specifically...

Snowflake’s Snowday ’23: Snowballing into Data Science Success

Snowflake’s Snowday ’23: Snowballing into Data Science Success

As we reflect on the insights shared during the ‘Snowday’ event on November 1st and 2nd, a cascade of exciting revelations about the future of...

How we interview and hire software engineers at Artefact

How we interview and hire software engineers at Artefact

We go through the skills we are looking for, the different steps of the process, and the commitments we make to all candidates.

Encoding categorical features in forecasting: are we all doing it wrong?

Encoding categorical features in forecasting: are we all doing it wrong?

We propose a novel method for encoding categorical features specifically tailored for forecasting applications.

How we deployed a simple wildlife monitoring system on Google Cloud

How we deployed a simple wildlife monitoring system on Google Cloud

We collaborated with Smart Parks, a Dutch company that provides advanced sensor solutions to conserve endangered wildlife...

Deploying Stable Diffusion on Vertex AI

Deploying Stable Diffusion on Vertex AI

This article provides a guide for deploying Stable Diffusion model, a popular image generation model, on Google Cloud using Vertex AI.

All you need to know to get started with Vertex AI Pipelines

All you need to know to get started with Vertex AI Pipelines

Presentation of a tool that demonstrates, practically, our experience using Vertex AI Pipelines in a project running in production.

dbt coalesce 2022 recap

dbt coalesce 2022 recap

The edition of dbt coalesce was taking place in New Orleans. And we learned a ton about the analytics engineering landscape.

Snowflake access control at scale

Snowflake access control at scale

Snowflake | How we automated the management of an account with more than 50 users while complying with data governance standards

Forecasting something that never happened: how we estimated past promotions profitability

Forecasting something that never happened: how we estimated past promotions profitability

A guide on how to use counterfactual forecasting to estimate the cost-effectiveness of past in-store promotions in retail.

Bayesian Media Mix Modeling with limited data

Bayesian Media Mix Modeling with limited data

How to estimate the impact of channels between Sales and Marketing? The Media Mix Modeling is the solution, Statistics are the main resource.

Measuring the CO2eq impact of your Python Notebook (Azure ML)

Measuring the CO2eq impact of your Python Notebook (Azure ML)

After my 1st story on code optimisation to reduce my computing time by 90%, I was interested in knowing the CO2eq impact saved by my...

A manifesto to include ML Engineers in your data science projects from day 1

A manifesto to include ML Engineers in your data science projects from day 1

Jeffrey Kane, Senior Data Scientist, explains why ML Engineer should be in your data science projects from day one.

What does the future of data engineering look like?

What does the future of data engineering look like?

The field and future of data engineering is evolving quickly. Discover 3 major trends I see become prominent in the coming years.

Is Facebook Prophet suited for doing good predictions in a real-world project?

Is Facebook Prophet suited for doing good predictions in a real-world project?

This guide will help you figure whether Facebook Prophet is appropriate or not for your forecasting project.

String filters in pandas: you’re doing it wrong

String filters in pandas: you’re doing it wrong

String filters in Pandas is something you should avoid as the scalar_compare operator leads to performance bottlenecks.

Data & ML challenges for 2022

Data & ML challenges for 2022

Key 2021 data & ML trends… and what they mean for 2022

How to quickly compare two datasets using a generic & powerful SQL query

How to quickly compare two datasets using a generic & powerful SQL query

A step-by-step guide to ease datasets comparison via a ready-to-use Structured Query Language template

Scoring Customer Propensity using Machine Learning Models on Google Analytics Data

Scoring Customer Propensity using Machine Learning Models on Google Analytics Data

A deep-dive on how we built state of the art custom machine learning models to estimate customer propensity to buy a product using Google Analytics...

The path to developing a high-performance demand forecasting model - Part 4

The path to developing a high-performance demand forecasting model - Part 4

Until now we have mainly talked about forecasting regular products that have been on the shelf for quite some time. But what about products that...