easy powerful and free

|
TADA – Predictive Modeling Software

Build Small Data powered with predictive modeling and transform your data into assets

Designed for domain experts, TADA by MyDataModels is a predictive modeling software that helps professionals use their Small Data to enhance their business with a light, easy to set up tool. It provides fast and usable results providing a predictive modeling solution. It’s not a problem if you’re not a data scientist. Based on the (r)evolutionary ZGP Engine, TADA is designed for business experts with no skills in coding nor data sciences.

How does it work?

Have your small datasets team up with predictive modeling to boost up your business

Set up meaningful datasets in a snap

Build and run machine learning models on any devices and platforms throught our powerful web-based pre-processing features: missing values management, stratified sampling, time series processing as well as automated variable reduction.

Predictive models
Predictive models

Easily train high performance models

Easily train and run high performance expressive models without writing a single line of code.  Within a few minutes, deliver high-end predictions for your business thanks to our modeling capability for binary, multi-classification and regression.

Optimize processes for speed and scalability

Create compact predictive models with 3 to 7 variables, operating on any accessibles devices to generate a predictive model within minutes. Runs seamlessly in cloud and desktop environments.

TADA predictive modeling

Deploy predictive models in a few clicks

Deploy and embed light and scalable auto ML predictive models for local insights and on-the-go permanent efficiency, through a call to a REST API endpoint (coming soon) or export your model’s code (Java, C++) into your application.

Prevent

detect

Predict

optimize

Solution for domain expert

it
Machine Learning for IoT applications
Is it possible to train and run predictive models based on historical Small Data in a small memory footprint and then embed it within an IoT device?...
Machine Learning for IoT applications
manufacturing
Failure Prediction
Is it possible to avoid partially or even totally industry downtimes? Can they be anticipated by using machine learning? Can the machines be repaired before they break down?...
Failure Prediction
medical
Pathology prediction for patient orientation
What if it was possible to help Emergency Call Centers Professionals to make a quick diagnosis based on a few questions, thanks to a machine learning tool? Could we help doctors and nurses diminish their diagnosis time?...
Pathology prediction for patient orientation
medical
Cardiovascular Disease Prediction
How could a general practitioner evaluate the risk of one of his patients having a heart attack within the next 24 hours?...
Cardiovascular Disease Prediction
medical
Breast cancer prediction
Is it possible, thanks to machine learning, to improve breast cancer prediction? Can we be more accurate in diagnosing whether a cell extracted from the breast is a cancer cell?...
Breast cancer prediction
Solution

Solutions

aviation
Transportation
Real estate
Real Estate
public app
Public Services
marketing icon
Marketing
IT
manufacturing
Industry
medical
Healthcare
bank and services
Finance & Services

See TADA in action

Discover TADA features

facilitate

Facilitate

Shift from days to a few hours into building ad hoc effective models with our 40% reduced time automated data preparation.

transform your data with tada

Transform

Get outcomes from your data without programming or machine learning skills needed and without any training requirement for yourself.

Icon Problems to solve

Create

Benefit from a lifetime free account to boost your business with the power of MyDataModels technology.

deploy predictive models

Deploy

Optimize your time with explainable and understandable models made of easy-to-read formulas.

challenge

Challenge

Achieve unrivalled performances on Small Data thanks to ZGP, our unique mathematical expression engine inspired by evolutionary algorithms.

accelerate data treatment

Accelerate

Turn your data into insights in a snap on any platform (cloud, desktop, mobile, edge). Create effective automated models without code conversion.

Powered by our core technology, theZGP Engine

ZGP : AI and mathematics at the service of your DATA.

ZGP combines two main fields of today’s AI: Symbolic Regression and Evolutionary Programming, to reach Zoetrope Genetic Programming achievement. It creates simple mathematical expressions that are particularly good at predicting or classifying Small Data. When most of today’s solutions take hours and hours (and a large amount of data) to produce decent result, ZGP produces much better models at a much faster pace.

After 10 years of research in AI, we continue to innovate.

We have now partnered with major research institutes (INRIA) to accelerate our research. We continue to invest massively in research and have built partnership with some of the most renowned mathematicians and researchers in the field. Like our algorithms, we evolve!

Multiple modeling & discriminating capacities

Binary classification, Regression and Multi-class classification modeling are available.  The modeling algorithm is able to consider a large number of variables during analysis and automatically select a minimal subset comprised of the most useful variables.

ZGP engine
data algorithm

Minimalistic & efficient

Models produced are minimalistic in the sense of having a minimum reliance upon larger quantities of independent variables. Models have a peak maximum efficiency when employing 3 to 7 independent variables. The algorithm is able to discern physical signals in small amounts of data, i.e very few rows

Understandable & insightful

Models produced are in the form of a human readable mathematical equation which can be deployed in computing languages (Java, C++). Having specific equations describing system behaviors enables both wide application and detailed exploration of underlying phenomena.

The algorithm produces accurate estimation of future model performance. The accuracy realized when a model is deployed closely matches that estimated by the modeling process