Devang Rathi

Create your portfolio with ProoV
ProoV
DE Verified work portfolio

ProoV Portfolio

Devang Rathi

mechatronics · manipal institute of technology

View the ProoV leaderboard

Projects

Certified

Self-directed project

Predictive Maintenance: Industrial ML for Fault Detection

Condition-Monitoring Engineer · AI / ML · August 2026

72/ 100

A ProoV case study · educational project, not employment

Built an end-to-end rolling-bearing fault detector on vibration data: plotted and interpreted a faulty snapshot, used kurtosis to capture impulsive behavior, trained a shallow decision tree on training bearings only, and evaluated it on held-out healthy and faulty bearings. The final memo defended a 0.60 alarm threshold with catch-rate, false-alarm, and cost figures, and identified the outer race as the likely fault location.

Graded against

  • Feature engineering (signal to honest numbers)25%
  • Held-out evaluation (honest measurement)25%
  • Cost-based threshold decision + memo25%
  • Compact model + embedded-budget justification15%
  • Plain-language explanation10%

Passed · pass mark 60/100

What stood out6
  • Used a depth-capped decision tree and explicitly stated depth 2 and 7 nodes against an embedded budget
  • Reported held-out catch-rate and false-alarm rate rather than evaluating on training data
  • Wrote a maintenance memo that ties the threshold to cost trade-offs and explains the fault in plain language
  • Leakage-Free Feature Engineering
  • Honest Held-Out Evaluation
  • Compact Interpretable Modeling
The work I submitted18 tasks

10 tasks · 6.1k characters · Python · 8 written answers · 407 words

  • Initial Prediction62 characters
  • Load Plot Signal CodePython · 1.9k characters
  • Load Plot Signal205 characters
  • Example Rms WorkedPython · 697 characters
  • Time Features143 characters
  • Freq FeaturesPython · 927 characters
  • Train Classifier363 characters
  • Evaluation Heldout288 characters
  • Threshold Decision332 characters
  • Decision Memo1.2k characters
  • Initial Prediction9 words
  • Load Plot Signal Code164 words
  • Load Plot Signal15 words
  • Example Rms Worked72 words
  • Time Features10 words
  • Freq Features82 words
  • Train Classifier31 words
  • Evaluation Heldout24 words

Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.

Verified certificateTamper-proof · issued by ProoV
Certified

Self-directed project

Energy and Renewable: Machine Learning for the Power Grid

Junior Machine Learning Engineer · AI / ML · August 2026

91/ 100

A ProoV case study · educational project, not employment

Built a leakage-free gas-turbine TEY predictor end to end using the 8 operational sensor features, excluding downstream CO/NOx emissions to avoid target leakage. Trained and compared a LinearRegression baseline and a tuned RandomForest on a genuine time-based holdout, then reported held-out MAE, RMSE, R2, residual behavior, and a concise model card with monitoring and limitations.

Graded against

  • Build and validate the model correctly35%
  • Optimize and evaluate honestly25%
  • Write the Model Card (clarity + honesty)25%
  • Explain it to a non-expert15%

Passed · pass mark 60/100

What stood out6
  • Correctly excluded CO and NOx as downstream leakage features and documented why
  • Used an earlier-years/later-years split instead of a random shuffle, preserving temporal validity
  • Reported MAE, RMSE, and R2 on held-out data and checked residual behavior
  • Provided a manager-friendly explanation that clearly states accuracy, trust basis, and failure mode
  • Leakage-Free Feature Selection
  • Time-Based Validation Discipline
The work I submitted20 tasks

12 tasks · 13 lines · Python, JavaScript · 8 written answers · 413 words

  • Problem Frame151 characters
  • Leakage Flags113 characters
  • Train Validate BaselinePython · 1.3k characters
  • Train Validate Forest931 characters
  • Train Validate124 characters
  • Tune Evaluate SetupPython · 1.4k characters
  • Tune Evaluate ResidualsPython · 2 lines
  • Tune Evaluate132 characters
  • Residual Read381 characters
  • Drift Monitor92 characters
  • Model Card1.8k characters
  • Teach BackJavaScript · 906 characters
  • Problem Frame9 words
  • Leakage Flags1 word
  • Train Validate Baseline136 words
  • Train Validate Forest72 words
  • Train Validate1 word
  • Tune Evaluate Setup101 words
  • Tune Evaluate Residuals92 words
  • Tune Evaluate1 word

Summarised on purpose — the submitted code and writing stay private so this page cannot be reused as an answer key. The full submission sits behind the verified certificate.

Verified certificateTamper-proof · issued by ProoV
2Projects completed
2Verified certificates
82Average score
Create your portfolio with ProoV