Complaint Analyzer

Clusters and deduplicates customer complaints to find root causes.

Industry	Level	Difficulty	Recommended mode
Finance & banking	2 of 5	Intermediate	flat

Coming soon

A complete, runnable Complaint Analyzer reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Complaints arrive in many channels and words.
• Root causes hide in volume.
• Regulators expect trend analysis.

How SrvDB powers Complaint Analyzer

1. Complaints are embedded and grouped by nearest neighbours.
2. Duplicates across channels are linked.
3. New complaints far from known groups are flagged.
4. search_batch processes daily volumes.

What changes

Today	With Complaint Analyzer on SrvDB
Manual tagging	Automatic grouping
Duplicates double-counted	Linked across channels
Trends spotted late	New clusters surface quickly

How it works

1. Ingest complaints.
2. Embed.
3. Group and deduplicate.
4. Report trends.
5. Track remediation.

SrvDB features it uses

• search_batch: runs many queries at once, in parallel inside Rust.
• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• Root-cause analysis
• Regulatory reporting
• Product issue detection
• Channel deduplication
• Vulnerable-customer signals
• Remediation tracking

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./complaint-analyzer-db", dimension=384)

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def similar_complaints(complaint, k=5):
    hits = db.search(embed(complaint), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Human review of groupings.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Finance & banking projects

Level	Project	What it does
1 · Beginner	Policy Assistant	Answers staff questions from internal policies and product terms.
2 · Intermediate	Complaint Analyzer (this page)	Clusters and deduplicates customer complaints to find root causes.
3 · Advanced	Fraud Pattern Matcher	Compares new cases with confirmed fraud cases and ranks them for investigators.
4 · Expert	Investigator Agent	An agent that gathers context across cases, policies and customer history.
5 · Frontier	On-prem Risk AI Platform	A data-resident AI retrieval platform for risk and compliance teams.

See also: Use cases · Live examples (coming soon)