Material Development with Artificial Intelligence

Material and compound development processes require significant time and countless iterations to find the optimal formulation. 

Uncountable enables R&D labs to cut development time and reduce testing iterations

Artificial intelligence algorithms suggest the best recipes to run, avoiding the constant minor alterations to individual ingredients. Complicated development processes that used to take countless, repetitive experiments can now be conducted in half that time utilizing advanced machine learning models.




step 1: ingest previous test data

Uncountable's software incorporates multiple data sources to build out a robust knowledge base, including property objectives, testing requirements, list of available ingredients, past formulations and test history. 

step 2: model material space

The software utilizes all information to build out a model of the material property performance "space". The use of artificial intelligence models allows the system to understand the effect of individual ingredients and interactions with the entire formulation.

Models from traditional DOE software that typically rely on linear regressions make oversimplifications and fail to capture the complexity of the development process.



step 3: suggest new recipes

Multiple new compound formulations are then delivered to the user for further testing. These suggestions are the result of a high dimensional optimization analysis, yielding optimized testing sequences and reduced trial cycles to the ideal material recipe.  This obviates the need for factorial testing where every combination of values is tried.

The machine learning engine is continuously improved by feeding further trial information into its base of test history, meaning a research team gets better and better at finding breakthrough materials. 

How our technology differs from a traditional design of experiment (DOE)

Traditional DOE's


  • Excel
  • DOE software like JMP & Mini-Tab

Modeling Techniques: 

  • Linear regressions
  • Large, fixed parametric models 

Formulation Testing Procedure: 

  • Orthogonal designs - vary few parameters at a time
  • Manual designs - somewhat arbitrary and manual proposal of new formulations 


Uncountable's Approach


  • Custom software designed for formulation science life cycle

Modeling Techniques: 

  • Machine learning models
  • Flexible, Bayesian models

Formulation Testing Procedure: 

  • New formulations chosen via artificial intelligence after simulating millions of combinations
  • Run experiments that are likely to outperform previous tests and provide more information about ingredient responses.


Download Our Case Study

Fill out the form below and check out our case study with a Fortune 1000 automobile supplier. 

Name *


Custom Web-Based Interface

We'll provide you everything you need to view and integrate our models. This starts with our cloud-based software solution that displays visualizations and reports customized to the needs of your company.



Data Exports and Add-On Integration

Integrate our insights into your existing workflow. The value we add is in the output of our advanced algorithms and statistical models. We will provide data exports and add-on support for the software you already use.


We will travel to your site to get your solutions up and running and ensure compatibility with your data sources. After delivering our software, we will continue to iterate with your help to produce the most profitable insights for your company.