Supported models and what's coming

Supported models and what's coming

A plain list of the models Kaimei explains today, the ones it explains through your own scoring endpoint, and the models and features coming soon.

#Explained today

Kaimei explains models that make one prediction from a fixed set of inputs. Each input is a number, a category, a yes/no flag, or an image.

Kind of modelExamplesHow it connects
Yes/no and multi-class decisions on structured dataCredit approval, fraud flags, churn, claims triageUpload it from scikit-learn, Keras or PyTorch, or connect a scoring endpoint.
Numeric predictions on structured dataDemand forecasts from features, pricing, loss estimatesThe same.
Image classificationDefect detection, document type from a scan, speciesUpload a convolutional network, or connect a scoring endpoint.
Models Kaimei runs through your endpoint, on the same kinds of inputNon-linear SVMs, nearest neighbours, naive Bayes, Gaussian processes, tree models with categorical splits, models written in other languagesA scoring endpoint you host, or attributions you compute. Running more of these directly is coming soon.

#Partly supported

  • Networks with attention, recurrent or upsampling layers. Kaimei draws the architecture, and running those layers itself is coming soon. Until then, connect a scoring endpoint to explain the model, provided its inputs are structured data or images.
  • Custom models. Kaimei runs tree ensembles of any size, linear models, neural networks and combinations of those itself; anything else, such as your own Python classes, needs a scoring endpoint.
  • Very wide inputs. Above 96 inputs, the Shapley methods first find the inputs that matter and report the rest as one remainder. LIME and KernelSHAP stop at 4,096 inputs.
  • Grad-CAM needs an image model whose layers were uploaded. Occlusion and LIME work for any image model.

#Coming soon: models and inputs

Kaimei explains one prediction from a fixed set of inputs today. These are the models and inputs we are adding, and what to use until each one ships.

Coming soonWhat Kaimei will explainUntil then
Text and language modelsSentiment, topic and document classifiers on raw text, with each prediction attributed to words and passages; large language models such as chat assistants, summarisers and code generators, through the score of a chosen answer.Explain the structured features you derive from the text, such as scores or counts.
Generative modelsModels that produce text, images or audio, through the score or likelihood of a chosen output.Register a score you derive from the output, such as a quality or safety score, as a numeric model behind a scoring endpoint.
Raw sequences and time seriesModels that read a history step by step, such as recurrent networks and temporal transformers, attributed per time step and per input.A forecasting model that takes fixed features, such as lagged values and rolling averages, works today.
Several outputs at onceMulti-output regression, multi-horizon forecasts and multi-label classifiers, with every output explained in one call.Register one model per output.
Boxes, masks and rankingsObject detection and image segmentation, explained per box or mask; recommendation and search ranking, explained per item's position.Image classification works today, and a ranker's score for one item can be registered as a numeric prediction.
Audio and videoAttributions per time span, frequency band or frame.A classifier on features you extract, such as spectral statistics, works today.
Clustering and reinforcement learningWhy a row falls in its cluster, and which observations drive a policy's action.A model that outputs a single anomaly score can be registered as a numeric prediction.
ONNX and Hugging Face uploadsModels exported to ONNX, including models written in other languages, and Hugging Face models, uploaded and run by Kaimei itself.Connect a scoring endpoint; the framework is recorded as a label.
More estimators, run directlyTree models with categorical splits, scikit-learn pipelines with encoders, non-linear SVMs, nearest neighbours and naive Bayes, read and run by Kaimei.Connect a scoring endpoint, or send attributions you compute.
Attention, recurrent and upsampling layersNetworks with these layers run by Kaimei, not only drawn.Kaimei draws the architecture; connect a scoring endpoint to explain the model.

#Coming soon across the platform

Beyond new kinds of model, these are the features we are building for the teams that explain, monitor and govern models.

Coming soonWhat it will doUntil then
Fairness and disparate-impact testingOutcome rates, adverse impact ratios and calibration compared across the groups you define, with a check for inputs that act as proxies for a protected characteristic.Explanations can help investigate a finding, but they are not a test.
Integrated Gradients and DeepLIFTGradient-based attributions computed by Kaimei for uploaded networks.Store the attributions you compute beside the built-in methods.
Adversarial robustnessGradient attacks such as FGSM and PGD, reporting how small a change flips each decision.The robustness analysis measures decision flips under random noise.
Challenger benchmarksA simple, interpretable model fitted to the same reference data, so validators can see what the complex model adds.Register a challenger yourself and compare the two models' insights side by side.
Scheduled checksDrift and performance analyses run by Kaimei on the schedule you set.Run them from your own scheduler, one API call each.
Alert routingMedium and high findings sent to email, Slack, Microsoft Teams, PagerDuty or a webhook.Alerts appear in the dashboard and in the organization and project overviews.
Data quality checksMissing values, out-of-range values, unseen categories and unit changes caught as predictions are logged.Drift compares live inputs with the reference data, feature by feature.
Attribution driftAn alert when what the model relies on shifts, not only its inputs.Compare the global importance from analyses run at different times.
Retention schedulesRecords deleted automatically once they pass the period you set.Records are kept until you delete them.
Policy rules beside the modelCut-offs, overlays and manual decisions recorded with each explanation, so it reflects the whole decision.Keep them in your decision system, under the same prediction_id.
Reason tablesApproved adverse-action wording kept in Kaimei under change control, so each explanation returns draft reasons and the inputs held for review.Keep the table in your code, as in Adverse action reasons.
Documentation reportsModel documentation and validation reports drawn from the structure, analyses and insights, exported as PDF or Word.Structure and insights export as JSON.
Single sign-on and provisioningSAML and OpenID Connect sign-in through your identity provider, with SCIM to add and remove people.Sign in with email and password, Google or GitHub.
Audit logWho signed in, created a key, changed a model or deleted a record, and when.Every prediction, explanation and analysis is stored with its time and model version.
ML platform integrationsRegister models straight from MLflow, Amazon SageMaker, Vertex AI and Databricks.Upload from your notebook or pipeline with the Python client.
An R clientThe same calls from R, for statisticians, actuaries and teaching.The REST API works from any language.

#By design

  • Cause and effect. An explanation describes how the model responds to its inputs, not what would happen in the world if an input changed.
  • Serving your model. Kaimei calls your model, or runs an uploaded copy, to explain and analyse it; your own systems keep serving customers.

If your model, or a feature you need, is not listed here, tell us about it. It helps us decide what comes first.