A machine learning model that analyzes time-series parametric data from electronic components to detect latent defects and drift during burn-in testing for quality assurance inspectors.
Indian Space Research Organisation(ISRO) · Department of Space / Indian Space Research Organisation · Software
Signing in saves it for your whole team — everyone on your invite link sees the same two entries. Anything you shortlisted while signed out comes with you.
Decomposed from what the description asks for. Nothing added.
Dynamic Outlier Detection
Build an outlier detection system that flags components based on batch context rather than absolute datasheet limits.
Time-Series Drift Predictor
Build a predictive regression model that takes early measurement values as inputs to forecast later values.
Drift Rate Evaluator
Calculate safety slopes to flag components for early rejection when the predicted drift rate exceeds limits.
Explainable Output
Provide justifications for model classifications so a quality assurance inspector can understand the decision.
Both columns are read off the brief's own wording. Nothing here is inferred from the ministry's name.
The evaluators will check your anomaly detection score with heavy penalties for false negatives, the mean absolute error of your drift predictions against hidden ground-truth values, and how well your model explains its classifications to an inspector.
A jury can still ask about these. Decide them deliberately rather than by accident.
Generated from the brief's own wording and the competition's published rules — never from a guess about what this ministry prefers.
What specific dataset or historical component logs will be used to train and test the model?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
What exact safety slope thresholds define an unacceptable drift rate?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.
The brief asks for dynamic outlier detection. How would you build that?
Decoded from SIH26170 itself — Build an outlier detection system that flags components based on batch context rather than absolute datasheet limits. The brief asks for it by name.
Each one is quoted from a gap in the brief, not a guess about your team.
Needs data you may not get
The problem requires analyzing specialized component burn-in parametric data like standby and leakage currents from high-reliability sectors such as space.
No measurable target
While it mentions mean absolute error and anomaly detection scores, it never states a specific target numerical threshold for success.
What the organisers attached, and what the brief assumes you can get.
Same organisation, same year. Reading two of theirs tells you more about what they care about than reading one.
Pick what you are about to do and copy the prompt. It carries the organisers' own wording, the constraints they never spell out, and an instruction not to invent requirements they never set.
Who has this problem, what already exists, and what you would have to find out.
The brief asks for time-series drift predictor. How would you build that?
Decoded from SIH26170 itself — Build a predictive regression model that takes early measurement values as inputs to forecast later values. The brief asks for it by name.
The brief asks for drift rate evaluator. How would you build that?
Decoded from SIH26170 itself — Calculate safety slopes to flag components for early rejection when the predicted drift rate exceeds limits. The brief asks for it by name.
The brief asks for explainable output. How would you build that?
Decoded from SIH26170 itself — Provide justifications for model classifications so a quality assurance inspector can understand the decision. The brief asks for it by name.
Where does your data come from — a published source, one you collect, or one you generate?
No dataset is attached to this problem statement, so sourcing it is part of the work and nobody told you that.
Why not use what already exists? Name the closest thing to this that is already running.
A team that has not named the alternative themselves is answering this for the first time in the room.
Which single thing will you demonstrate end to end, start to finish, with nothing skipped?
Ours, not a rule: a narrow thing that fully works survives questioning better than a broad thing that half works. If nobody on the team can name it, that is the finding.
Show me this working: the evaluators will check your anomaly detection score with heavy penalties for false negatives, the mean absolute error of your drift predictions against hidden ground-truth values, and how well your model explains its classifications to an inspector.
This is the evaluator read for your problem statement, decoded from the brief's own wording.