We are currently in closed beta. If you are interested in becoming a design partner, please reach out. Alternatively, sign up to our Waitlist

Take a linear model:

Feature X Target Y 1.0 2.0 3.0 4.0 5.0 1 2 3 4 5 Data points Confidence interval Regression line

Deploy it to a unique API with diagonal.sh

Query your model from anywhere:

johndoe % curl -X POST \ -H "Content-Type: application/json" \ -H "X-API-Key: ${API_KEY}" \ -d "{\"data\": [5.0, 2.0, 0.0, 1.0, 3.0, -2.0, 1.0, 0.0, 2.0, 0.0], \"model\":\"${MODEL_ID}\"}" \ "https://infer.diagonal.sh/${ROUTE}" {"message": "3.71"}

High Performance APIs

Low Base Cost

For linear models, hosting is priced at 0.1 Euro/day (minimum 10 days)

Low Incremental Cost

For linear models, the first 30k requests are priced at 1 Euro/1k requests, and subsequent requests at 1 Euro/10k requests

Low Latency

Native deployments and (in the future) multi-region support enable best-in-class request latency

High Availability

99.9% uptime

High Throughput

Model inference that can scale to 10k+ requests per second

Automatable

Model deployment, updates and deletion can be done through the API

Where do I start?

Industry

Finance

Credit and risk scoring across consumer finance, real estate, insurance & reinsurance and financial markets is commonly done with linear models due to their reliability and interpretability. Whenever these models need to be integrated into an app, website, or internal service they need to be deployed to the web, usually as an API.

FMCG

Sales and demand forecasts are commonly done via linear models, as these are often have good performance and high levels of reliability. Other common applications include marketing ROI modelling, pricing optimization and inventory management. If these need to be regularly done based on changing data, and done consistently across time and the organisation, deployment via API is your friend.

Market research

Customer segment classification, decision modelling and quantitative market modelling are generally done via linear models. Deploying these via API expands their effectiveness for customers.

Economic & Policy Consulting

Forecasting models, risk assessment models, macroeconomic models and many other kinds of models routinely produced in economic and policy consulting benefit from API deployment, which enables customers to evaluate their situation using new data as it becomes available

Online services

Customer churn prediction, newsletter optimization, UI personalization and many other modelling tasks can be done using linear models. Once deployed via API, they can improve the user experience and increase company effectiveness.

Cybersecurity

Anomaly detection, threat scoring and fraud detection are common usecases for linear models. Through API deployment, these techniques can be applied consistently through an organization or product. diagonal.sh enables frequent updating of these models as the threat landscape evolves.

Online gaming

Content optimization and game play adaptation can be dynamically learned from user behavior using linear models, and quickly fed back into the game play experience via APIs.

International development

Impact modelling and forecasting of more general (macroeconomic or ecological, for example) and more specific variables in international development is frequently done using linear models, as they guarantee reliability and interpretability. Deploying them via API can make these models useful and responsive to new data across the world.


Model type

Linear regression

Linear regressions and variants such as Ridge regression and Lasso are one of the two model types with first-class support on diagonal.sh

Logistic regression

Logistic regressions for classification are the second model type with first-class support on diagonal.sh

Online learing

Through the update logic, both linear and logistic regression models can be adapted to new data as it comes in, and enable online-learning versions of these algorithms

Contextual bandit

Through multiple online-learning linear regressions, contextual bandits can be implemented fairly straightforwardly on diagonal.sh