Converged Overview One database. Every data model. On Exadata.
🛡 Data stays in-region · Autonomous AI Database
One Converged Database. On Exadata.
This entire application runs on a single Oracle Autonomous AI Database. Relational, JSON documents, AI vectors, text, spatial, graph, in-database machine learning and natural-language Select AI — all on the same data, in one engine, in-region. No warehouse + vector DB + document store + geo service + graph DB to stitch together, secure separately, and copy data between.
Live data-model inventory — all in one MAXIS schema
Every tile below is a different data model, queried live from the same database on this page.
Risk band distribution ML Scored by in-database Random Forest
Churn rate by contract type SQL Month-to-month is the churn engine
Churn by ARPU band SQL Where the high-value risk sits
Churn by tenure cohort SQL Early-life subscribers churn most
Revenue & churn by segment SQL Enterprise is the growth engine
Segment Account type Subscribers Monthly revenue Avg ARPU Churn
Subscribers & churn across Malaysia SPATIAL
Bubble size = subscribers, colour = churn rate. Positions from SDO_GEOMETRY points.
By state SQL State Region Subs Churn Revenue
Network sites by distance from KL core SPATIAL Geodesic distance via SDO_GEOM.SDO_DISTANCE
High-risk subscribers — recommended retention actions ML
Click a row for the full case file. Contact fields are redaction-protected.
Subscriber Churn Risk Segment State Recommended action Approval
Subscriber Explorer SQL
Browse the relational base table. Filter by state; click a row to open the JSON 360 document.
Subscriber Segment Account State Contract Mobile ARPU Tenure Churned
Model leaderboard ML 5 algorithms trained in-database with Oracle Machine Learning — no data extracted to an external ML platform
Algorithm Accuracy Precision Recall F1 Production
Knowledge base TEXT VECTOR Policy documents chunked and stored in-database, ready for vector + text retrieval
Sovereign Policy Copilot RAG
Retrieval-augmented answers grounded in the in-database documents — the documents never leave Oracle
Ask
Ask the Data SELECT AI
Natural language to SQL with Oracle Select AI. Only the schema description is sent to the model — never subscriber data.
Ask
🛡 Only the schema description was sent to the model — no subscriber data left the database. Oracle generated this SQL, which runs in-region:
Subscriber 360 document JSON
The same subscriber as a native JSON document. Relational and document models over one dataset — no separate document store.
Load document
JSON document Load a subscriber to view its document.
Service adoption computed inside the JSON array JSON_TABLE Aggregated directly over the documents' services[] arrays — no flattening, no ETL
Referral network — top influencer GRAPH
Multi-hop network reach computed by graph traversal over the referral relationships
Top influencers by network reach GRAPH Direct referrals vs. total reach across up to 4 hops
Influencer Segment State Direct Network reach Hops