Our software takes engineers from data to a prediction: check the data, train models, assess and export results. In the browser or fully on premise.
Engineers, specialist teams, IT and procurement
A guided flow from import through data description and assessment to training and prediction. Random Forest, XGBoost, FNN and RNN, also in batch; Pro adds Optuna.
What you get Ready to use in the browser, no installation
The same flow, fully local and offline-capable. Projects and models stay on your hardware as .dvp and .dvm files.
What you get An AI tool for sensitive engineering data
Licences for individual users, teams and companies, optionally with training hours, an on-site workshop and support. Training and prediction-only roles can be separated.
What you get One tool for your team, with onboarding and a named contact
Load a CSV, check separator and columns, choose inputs and target.
Review distributions, correlations, Data Size Analysis and Input Dropout.
Pick a model type, configure, train and check the quality metrics.
Score new cases, export results, save the model as .dvm.
A neural network predicts the residual wall thickness of a hollow plastic part from its process parameters. Run in reverse, it returns the process setting needed for a target wall thickness. A project with Plastic Innovation.
→ View projectA neural network trained in dAIve Predict predicts the thermal conductivity of gas mixtures used in insulating glass units. A demonstration case based on literature data.
→ View project
Load a CSV and choose inputs and outputs. Here: four airfoil parameters, targets are the drag and lift coefficients.
Real recording of the web app · demo project NACA airfoils (lift and drag)
Start the trial in your browser or talk to us about desktop and team licences.
