analytics-cloud-rpt15-prediction-demo

RPT-1.5 Payment Delay Prediction — SAP Analytics Cloud Demo

Description

Run RPT-1.5 predictions directly from SAP Analytics Cloud (SAC).

This project is the backend for an end-to-end setup that predicts how many days late a customer will pay. RPT-1.5 is deployed in SAP AI Core, the data lives in SAP Datasphere, and this FastAPI service — deployed to Cloud Foundry — wraps the prediction call. From SAC, a Multi Action button triggers the prediction, polls for the result, and writes the predicted values back so they show up in a story.

How it works

SAC Multi Action  ──POST /predict──▶  FastAPI (Cloud Foundry)
      │                                     │
      │                                     ├─ read V_PAYMENT_DELAY_PREDICTION (Datasphere / HANA)
      │                                     ├─ call RPT-1.5 deployment (AI Core)
      │                                     └─ write predictions → PREDICTION_RESULTS (HANA)
      │                                     │
      └──GET /predict/{job_id}──poll──────▶ status / result

1. SAC calls POST /predict, which starts a background job and returns a jobId plus a Location header (async pattern SAC's External API step expects).
2. The job reads every row from the V_PAYMENT_DELAY_PREDICTION view. Rows with a NULL Days_Late are marked [PREDICT]; all other rows are sent as context so RPT-1.5 can make accurate in-context predictions.
3. Predictions (value + confidence interval) are upserted into a staging table (<HANA_USER>.PREDICTION_RESULTS).
4. SAC polls GET /predict/{job_id} until the job is done, then reads the results back into the story.

Project structure

API

All endpoints require HTTP Basic auth (API_USERNAME / API_PASSWORD).

Requirements

• SAP AI Core with an RPT-1.5 Large deployment
• SAP Datasphere / SAP HANA Cloud with a V_PAYMENT_DELAY_PREDICTION view
• Cloud Foundry space (SAP BTP) for deployment
• Python 3.10+

Download and Installation

Run locally

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env   # then fill in your values
uvicorn main:app --reload

Run the prediction pipeline directly (without the API):

python prediction.py

Deploy to Cloud Foundry

cf push

Set the environment variables in Cloud Foundry (e.g. cf set-env rpt1-demo <KEY> <VALUE>) or bind them through a service — do not commit your .env.

Configuration

Copy .env.example to .env and fill in the values:

• SAP HANA Cloud — HANA_HOST, HANA_PORT, HANA_USER, HANA_SCHEMA, HANA_PASSWORD
• SAP AI Core — AICORE_AUTH_URL, AICORE_CLIENT_ID, AICORE_CLIENT_SECRET, AICORE_BASE_URL, AICORE_RESOURCE_GROUP, RPT1.5LARGE_DEPLOYMENT_ID
• API auth — API_USERNAME, API_PASSWORD

Known Issues

No known issues.

How to obtain support

Create an issue in this repository if you find a bug or have questions about the content.

For additional support, ask a question in SAP Community.

Contributing

If you wish to contribute code, offer fixes or improvements, please send a pull request. Due to legal reasons, contributors will be asked to accept a DCO when they create the first pull request to this project. This happens in an automated fashion during the submission process. SAP uses the standard DCO text of the Linux Foundation.

License

Copyright 2026 SAP SE or an SAP affiliate company and analytics-cloud-rpt15-prediction-demo contributors. Please see our LICENSE for copyright and license information. Detailed information including third-party components and their licensing/copyright information is available via the REUSE tool.