Welcome to DataInsight !

 

Your partner to

unlock your business potential through Data & AI

Main services:

 Data & AI STRATEGY: Unlock your potential

AI is promising to revolutionize every business, but how to put a relevant strategy in place for yours?

You don't have to take this journey alone!

DataInsight can help you crafting your Data & AI strategy in three steps:

• Definition
• Implementation
• Governance & Maintenance

 Generative AI PROJECTS & solutions for improved growth

The Generative AI toolbox is fascinating and can deliver many business solutions not even imaginable before !

However, it might be difficult to identify the best approach in terms of data security, algorithm efficiency, and scalability on the long run.

Data-driven PRODUCT development through advanced analytics and modeling

On top of the quality and cost of a solution, "time to customer" is very often a critical parameter to win a business opportunity.

Using smart approaches for product development (e.g. design of experiment, incl. adaptive design, and advanced modeling) enables better and fast development of solutions

Recent collaborations

 

 

"Nicolas is a go-to expert. His practical, consumer-centric approach combined with strong skills in statistics, design of experiments, and modelling consistently yield relevant insights and ideal solutions. His expertise in AI is also highly valued for advancing our company's initiatives."

"Recommended by SensoStat, Nicolas was instrumental to help us building knowledge about one of our product. He expertly guided us through a series of design of experiments, rapidly building product understanding and modelling results. This enabled us to accurately predict product properties and ensure consistent quality, truly elevating our product improvement process"

 

"We initiated a collaboration with DataInsight to develop an advanced predictive model to forecast the number of laser tattoo removal sessions depending on patient and tattoo characteristics. Based on carefully collected historical data at Riviera Clinic, the approach developed by Nicolas enabled the identification of the most influencing parameters as well as their interaction mechanisms.

 

The resulting predictive model demonstrated significant improvement over existing standards and has been recently published in a peer-reviewed journal."

 

 

About me

I am Nicolas Pineau, food engineer and food scientist by education (and good food addict :) ), rapidly evolving towards the world of data, data science and AI. I started this data-driven journey since my PhD in sensometrics (data science applied to sensory and consumer studies), and never looked back since then.

My academic background mainly addresses sensometrics topics, like preference mapping, sensory panel performance, temporal dominance of sensations, and meta-analysis (more details about some papers and other scientific activities below).

Industry wise, I worked for 16 years at Nestlé Research, Switzerland, promoting good data handling principles to leverage internal data (data office), contributing to ISO norms definition, building numbers of designs of experiments and predictive models for product development, developing academic collaborations for methodological developments, as well as strategic partnership with other industries and start-ups to leverage external capabilities and improve internal competences. Among my main contributions, I put in place the data ecosystem for sensory and consumer science (200+ users, impact on all product categories) from data collection and curation to dashboarding and advanced analytics. I also led the transversal data science R&D network for a while (about 50 people), fostering interactions between data professionals from various horizons and business leaders and promoting the use of new technologies like Natural Language Processing and Knowledge Graphs to accelerate innovation through consumer listening. 

Then, I moved to the U.S. and worked at Archer Daniels Midland (ADM) as director R&D AI and I2L data officer. In this role, I shaped the AI roadmap for R&D and promoted the use of AI for various applications, like the use of LLMs connected to internal data to leverage company knowledge, the transfer of Generative AI techniques to product formulation, or the dive into molecular dynamics simulations. Under my data officer role, I proposed a global framework to handle all R&D data through a modular approach, while ensuring optimal data security.

Scientific activities

Selection of most relevant papers out of the 30+ publications in international journals

• Menozzi, C., Pineau, N. (2025). A new predictive model for tattoo removal: leveraging patient and tattoo characteristics, Journal of Cosmetic Dermatology. – dermatology application. link
• Lawlor, B., Bavay, C., Van Hout, D., McEwan, J., Dreyfuss, L., Labbe, D., Groeneschild, C., Marcelino, A.S., Rason, J., Worch, T., Piqueras-Fiszman, B., Lê, S., Pochart, N., Mehring, P., Pineau, N. (2025). Digitalization in sensory and consumer science – summary perspectives from presentations at the 15th Pangborn sensory science symposium. Food Quality and Preference, 124, 105372 – opinion paper
• Antille, N., Audoubert, F., Camilleri, M., Grain, M., Rytz, A., Pineau, N., Mahieu, B. (2024). Comparison of check-all-that-apply to collect reasons for liking and disliking chocolates in preference mapping. Food Quality and Preference, 117, 105171 – method comparison including Natural Language Processing elements
• Moser, M., Lepage, M., Pineau, N., Rytz, A. (2020). Is statistical power necessary to quantify the impact on study conclusions of moving from two to one assessment? Food Quality and Preference, 79, 103651 – theoretical debate among experts
• Pineau, N., Moser, M., Rawyler, F., Lepage, M., Antille, N., Rytz, A. (2019). Design of experiment with sensory data: A pragmatic data analysis approach Journal of Sensory Studies, 34(2), e12489 – reference paper at corporate level for data analytics standards
• Perrot, M., Pineau, N., Antille, N., Moser, M., Lepage, M., Thaler, T., Voirin, A., Rytz, A. (2018). Use of multi-market preference mapping to design efficient product portfolio. Food Quality and Preference, 64, pp. 238-244 – reference paper at corporate level for preference mapping
• Rytz, A., Moser, M., Lepage, M., Mokdad, C., Perrot, M., Antille, N., Pineau, N. (2017). Using fractional factorial designs with mixture constraints to improve nutritional value and sensory properties of processed food. Food Quality and Preference, 58, pp. 71-75 – new Design of Experiments methodology
• Robin, F., Heindel, C., Pineau, N., Srichuwong, S., Lehmann, U. (2016). Effect of maize type and extrusion-cooking conditions on starch digestibility profiles. International Journal of Food Science and Technology, 51(6), pp. 1319-1326 – food extrusion process
• Lepage, M., Neville, T., Rytz, A., Schlich, P., Martin, N., Pineau N. (2014). Panel performance for Temporal Dominance of Sensations. Food Quality and Preference 38, pp. 24-29 – advanced temporal statistics
• Labbe, D., Pineau, N., Martin, N. (2013). Food expected naturalness: Impact of visual, tactile and auditory packaging material properties and role of perceptual interactions. Food Quality and Preference, 27(2), pp. 170-178 – concept of naturalness
• Pineau, N., de Bouillé, A., Lepage, Lenfant, F., Schlich, P., M., Martin, N., Rytz, A. (2012). Temporal Dominance of Sensations: What is a good attribute list? Food Quality and Preference, 26(2), pp. 159-165 – reference paper for TDS method (+100 citations)
• Robin, F., Dubois, C., Pineau, N., Schuchmann, H.P., Palzer, S. (2011). Expansion mechanism of extruded foams supplemented with wheat bran. Journal of Food Engineering, 107(1), pp. 80-89 – food mechanisms
• Meyners, M., Pineau, N. (2010). Statistical inference for temporal dominance of sensations data using randomization tests. Food Quality and Preference, 21(7), pp. 805-814 – theoretical work on randomization
• Ross, A.B., Pineau, N., Kochhar, S., (...), Beaumont, M., Decarli, B. (2009). Validation of a FFQ for estimating whole-grain cereal food intake. British Journal of Nutrition, 102(11), pp. 1547-1551 – study on food intake questionnaire
• Pineau, N., Schlich, P., Cordelle, S., (...), Etiévant, P., Köster, E. (2009). Temporal Dominance of Sensations: Construction of the TDS curves and comparison with time-intensity. Food Quality and Preference, 20(6), pp. 450-455 – reference paper on TDS (+400 citations)

Book chapters

• Schlich, P., Pineau, N. 2017. Temporal dominance of sensations, in Time-Dependent Measures of Perception in Sensory Evaluation . pp. 283-321. Woodhead publishing, WPF 274, ISBN: 978-178242258-7, 978-178242248-8
• Pineau, N., Schlich, P. 2015. Temporal dominance of sensations (TDS) as a sensory profiling technique, in Rapid Sensory Profiling Techniques and Related Methods: Applications in New Product Development and Consumer Research pp. 269-306. Wiley Blackwell, ISBN: 978-111899168-8, 978-111899162-6

Other scientific activities

• Consultant for ML & AI strategy, sensory and consumer science, Design of Experiments, Data Science
• Invited speaker at Pangborn international symposium 2023, FlavorCon 2024, MarkLogic World 2025
• President of the organising committee for Agrostat 2016 and of the scientific committee for Agrostat 2022
• President of the Agroindustry group of the French Society of Statistics (2017-2023)
• Award of the “Generative AI expert of the year 2024” by Progress