About us
Being at the intersection of AI and fashion, Heuritech offers a unique and thorough point of view of what consumers will be looking for next. Our AI platform offers a comprehensive guide beyond superficial analysis, backing up every intuition with solid data insights.
Working together with clients
BUILT FOR fashion BRANDS,
POWERED BY STATE-OF-THE-ART
ARTIFICIAL INTELLIGENCE
Pronunciation: hjʊ(ə)ˈrɪtek
Definition: the art of making discoveries by finding the most optimal solution in the unknown
Origin: our name, Heuritech, is a combination of the words Heuristic and Technology.
Heuristic comes from “Eurisko”, the greek word for “find”, which led to the famous expression “Eureka”.
Heuritech is a cutting-edge fashion technology company that offers brands predictive analytics on trends and products.
Using advanced artificial intelligence (AI) to translate real-world images shared on social media into meaningful insights, Heuritech empowers fashion brands to forecast demand and trends more accurately, produce more sustainably, and achieve unprecedented competitive advantage.
The company was founded by PhDs in 2013 with one goal in mind: to bridge the gap between artificial intelligence and business, two worlds often set apart. Several years later, Heuritech continues to apply the latest scientific research in the fashion industry.
Company founded by 2 PhDs in Machine Learning at Sorbonne University and subsequent development of the technology
First clients signed throughout various industries
Heuritech’s first Deep Learning Meetup in Paris
Team of 10 employees, including 8 PhDs in Machine Learning
€1,1 million fundraising round
Shift towards the fashion industry with proprietary computer vision to detect fashion attribute
Creation of our first platform: Product Insights
Winner of the LVMH Innovation Award as a solution dedicated to luxury
Solution scaled to sports and mass-market industries
First fashion weeks report
Creation of our second platform, Market Insight, with a trend forecasting algorithm
€4 million fundraising round
Team of 45 employees
Creation of New Data for Fashion, a community providing fashion brands with free information during Covid
Launch of the second version of our Market Insights platform
Launch of Heuritech Executive Community, to gather C Levels from our industry around sustainability and innovation
Additionally to our country-level panels, we now quantify the adoption of your products vs competition in sports races and specific locations / cities
Artificial
intelligence
research is in
our dna
Research is at the heart of Heuritech, as its 2 founders hold a PhD in Machine Learning. We remain at the forefront of Deep Learning and Computer Vision by publishing papers at top conferences (CVPR, ICCV, …), and organizing conferences in Paris.
Research is at the heart of Heuritech, as its 2 founders hold a PhD in Machine Learning. We remain at the forefront of Deep Learning and Computer Vision by publishing papers at top conferences (CVPR, ICCV, …), and organizing conferences in Paris.
Hear from the best - our clients
“What Heuritech is so good at is scanning a huge swath of information on social media, and then consolidating it into digestible chunks.”
sean mcdowell
vp design & development at sperry
“We had some intuitions that we wanted to test and Heuritech helped us to validate those intuitions.”
DAMIEN BERTRAND,
FORMER GENERAL MANAGER AT DIOR
“Not only can we see our products in theses images, but we can indentify trends, with people posting, and understand more about how our products are appearing in the wild and how people are using them to build their own identities.”
ian rogers,
FORMER chief digital officer of lvmh
“What we like about the ability to use social media is that it’s pure consumer intention. We are able to find what people say they actually want so we can start to design into statistical intention.”
Barry MCGEOUGH,
Former Global vp of innovation at Wolverine worldwide
“The collaboration with Heuritech brought a vision of the product not only in the fashion system but also with the real customer.”
bastien daguzan,
Former ceo at paco rabanne
Built for fashion brands, powered by state-of-the-art artificial intelligence
Heuritech is a cutting-edge fashion technology company that offers brands predictive analytics on trends and products.
Using advanced artificial intelligence (AI) to translate real-world images shared on social media into meaningful insights, Heuritech empowers fashion brands to forecast demand and trends more accurately, produce more sustainably, and achieve unprecedented competitive advantage.
The company was founded by PhDs in 2013 with one goal in mind: to bridge the gap between artificial intelligence and business, two worlds often set apart. Several years later, Heuritech continues to apply the latest scientific research in the fashion industry.
An award winning company
with strong industry recognition
“Heuritech has turned social media into an artificial intelligence tool that predicts the development of trends”
“The world’s first artificial intelligence (AI) service that can predict fashion trends”
“Heuritech is a technology company that uses artificial intelligence to browse images on social media to discern fashion trends”
WHAT IS ARTIFICIAL INTELLIGENCE ?
WHAT IS ARTIFICIAL INTELLIGENCE ?
We define Artificial Intelligence as intelligent programs that achieve tasks typically tackled by humans. The specific domain we focus on is deep learning, a breakthrough that has been revolutionizing artificial intelligence since 2010. We apply deep learning techniques to image recognition, allowing this technology to autonomously learn to recognize concepts that make sense for us humans, such as fashion details like colors, shapes, or materials.
PhDs in Artificial Intelligence
scientific papers published at international conferences
precision of our forecasting model
years of historical data
PhDs in Artificial Intelligence
scientific papers published at international conferences
precision of our forecasting model
years of historical data
a state-of-the-art artificial intelligence for images
Our industry-leading visual recognition technology accurately analyzes 3 million images everyday
We work toward viable engineering solutions where we aim to use our latest developments to build a Computer Vision pipeline that can analyze all clothing very precisely, at scale, from millions of images each day. Since typical Deep Learning open sources libraries do not work for unconstrained images, handling the unexpected is the main topic of our research.
our artificial intelligence forecasting methodology
Step 1
Define representative panels
From hand-picked fashion-forward influencers to AI-built mainstream segments for each geography.
Step 2
Apply our computer vision technology
To millions of social media images stemming from these panels to give you an unbiased quantifiable overview of the market behavior. More than 3000 fashion details can be spotted like shapes or fabrics.
Step 3
Use our machine learning forecasting algorithms
To predict what is coming next up to one year in advance with 90% accuracy. Our forecasting toolkit includes a master algorithm that uses optimal ensembling based on a combination of 7 forecasting algorithms.
Step 4
Insert Heuritech’s data into our market intelligence platform
We produce actionable insights for our clients within our personalized platform. Creative and analytical profiles can access images, analysis, and market forecasts to stay in tune with the market and optimize decision making
built for fashion brands, powered by state-of-the-art artificial intelligence
from the artificial intelligence lab to business
At Heuritech, we believe that climate change and environmental issues should be a priority for all companies. While our main focus is helping fashion brands to produce more mindfully and reduce their overstock, we all want to have a more direct impact, through The Lab.
our research papers on image analysis, deep learning & time series forecasting
| Statistics and Computing 2023 | Identifiability of discrete input–output hidden Markov models withexternal signals |  |
| Transactions on Machine Learning Research 2023 | HERMES: Hybrid Error-corrector Model with inclusion of External Signals for nonstationary fashion time series | |
| CVPR 2022 DyTox | Transformers for Continual Learning with DYnamic TOken eXpansion | |
| ArXiv 2021 | Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation | |
| CVPR 2021 PLOP | Learning without Forgetting for Continual Semantic Segmentation | |
| CVPR-Workshop 2021 | Insights from the Future for Continual Learning | |
| CVPR-Workshop 2021 | Continuum: Simple Management of Complex Continual Learning Scenarios | |
| ECCV 2020 | PODNet: Small-Tasks Incremental Learning | |
| CVPR 2019 | MUREL: Multimodal Relational Reasoning for Visual Question Answering | |
| AAA 2019 | BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection | |
| AAA 2019 | BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection | |
| ArXiv 2018 | OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation | |
| ICCV 2017 | MUTAN: Multimodal Tucker Fusion for Visual Question Answering | |
| ICCV Fashion Workshop 2017 | Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction | |
deep learning meetups
Heuritech is the founder and organizer of Deep-Learning Paris Meetup, a community of 5000 researchers gathering once a month.
the lab blog: artificial intelligence
our commitment
to privacy
Heuritech only analyzes public social media content. Our added value is in statistical aggregated data, therefore we never sell personal data.
from the artificial intelligence lab to business
Heuritech was founded in 2013 by Tony Pinville and Charles Ollion, after completing their PhDs in deep learning at the Pierre and Marie Curie University in Paris. The founders were dedicated to research and developed a state-of-the-art visual recognition technology to capture the power of fashion images shared each day online.
The team has a good balance of fashion and tech professionals. It's comprised of PhDs in machine learning, data scientists, and fashion experts.
After meeting with Louis Vuitton in 2015, the team decided to build an all-in-one solution, designed for the collection development process, which delivers the most significant business impact for fashion brand’s merchandising, product, and marketing departments.
Heuritech empowers fashion brands to fuel creativity, produce more sustainably, and improve profitability with cutting-edge artificial intelligence and comprehensive data.
from the artificial intelligence lab to business
years of Research & Development
people
PhDs in machine learning
fashion experts
years of Research & Development
people
PhDs in machine learning
fashion experts
Our executives and managers
Charlotte Fanneau
CRO & board member
> Expert in product development & marketing strategies
> HEC Paris in tech entrepreneurship
Tony Pinville
CEO & Co-Founder
> 15 years of experience as Head of R&D
> PhD in AI and Machine Learning
Lorraine Sailly
Chief Product & Data Officer
> 7-year experience in Data Consulting and AI Product Management
> ESSEC Business School
Thomas Robert
VP Engineering
> 8-year experience in Deep Learning
> PhD from Sorbonne Université in Deep Learning
Julie Pont
Fashion & Creative Director
> 11-year experience in Fashion Industry
> Fashion & Anthropology researches - IFM
Paul Tonelli
Head of Infrastructure
> 9-year experience as a system architect
> PhD from Sorbonne Université, A&M Engineer
Jean Bellot
Data Lead
> 8 years experience in Data science
> PhD in AI and Machine Learning from Sorbonne University
Sylvain Koos
Engineering Lead
> 10-year experience in CS & software engineering
> PhD from Sorbonne Université, INSA Engineer
Paul Morel
Head of Data Science
> 4-year experience in deep learning
> Polytech Sorbonne & IAE Sorbonne
Our partners & investors
