Major project Insurance Case Studio

Driving score from phone sensors

Inspired by publicly reported work at Progressive

Score how safely someone drives from phone sensor data, and turn the score into a fair discount.

The brief

Progressive has described Snapshot, which personalises rates from driving behaviour, and has published findings that hard braking and phone use go with more crashes and claims. Build a telematics product of your own: detect harsh braking, acceleration and phone handling from recorded sensor data, combine them into a driving score, and map the score to a discount. Good looks like: event detection checked against labelled driving, a score that separates aggressive from normal drivers, a discount table, and a privacy and fairness note.

Read the case first

What Progressive has said in public about this kind of work, on its own pages:

Make it your own

Score riding instead of driving: two-wheelers, delivery riders or auto drivers, on Indian roads. Record a few of your own trips (safely, as a passenger) and show where the model trained on the open data gets them wrong.

AITeky has no link with Progressive, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as Progressive's work or system.

What you will build

Process phone accelerometer and gyroscope readings labelled by driving style
Detect harsh braking, acceleration and swerving
Classify driving style from trip features
Combine events into a 0–100 driving score
Map the score to a discount and test it on claim data
Build a driver app mock-up and a privacy and fairness note

Free, open data to build it with

It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.