Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26184High risk high rewardacceptance 2/5

Development of a Predictive Analytics Framework for Cybercrime Complaints to Forecast Likely Cash Withdrawal Locations in Advance, Enabling Generation of Actionable Intelligence for Timely and Proactive Cybercrime Intervention.

Ministry of Home Affairs · Blockchain & Cybersecurity · Software

A valuable idea with no accessible data — the model would train and validate entirely on complaint patterns you invented, so it can only rediscover your assumptions, and the predictive-policing framing carries fairness risks worth naming rather than a demonstrable forecast.

What it actually is

The national cybercrime portal gets around 8000 complaints a day, and stolen money is usually withdrawn as cash somewhere before it can be frozen. The ask is a predictive framework that forecasts the likely cash-withdrawal locations in advance from complaint patterns, so police can pre-position teams and alert banks and ATMs in high-risk areas before the money is gone.

What to build

A predictive analytics framework over cybercrime complaint and fraud-flow data that forecasts likely cash-withdrawal locations for in-progress fraud cases — learning from historical complaint patterns, fund-mule networks and withdrawal geographies which areas and ATMs are probable cash-out points — and generates actionable intelligence so I4C-coordinated state and local police can pre-position teams and alert banks and ATMs in high-risk locations, feeding the financial fraud reporting system to speed fund blocking and improve recovery.

Smallest thing that wins the room

Feed a batch of complaint and fund-flow records and show the framework ranking a set of districts and ATM clusters by predicted cash-withdrawal likelihood for active cases, with the high-risk locations surfaced as an alert an investigator could act on.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Quiet70–160 teams expectedroughly 1 in 60–139 wins it

Quieter than 79% of the 226 · #49 of 226 by expected field

Few teams are likely to go here. The best odds on the board come from statements like this.

Why: defence, intelligence and space bodies drew small fields.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • Spatiotemporal fraud-flow prediction
  • Synthetic complaint/withdrawal data generation
  • Mule-network and geography modelling
  • Risk-ranked location forecasting
  • GIS alerting dashboard
  • Fairness / false-positive consideration
  • Predictive policing
  • Financial crime analytics
  • Spatiotemporal forecasting

Prior art to read before you start

cash-withdrawal location prediction · proactive fraud intervention · complaint-driven risk forecasting

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.