Piyush Thakur

Create your portfolio with ProoV
ProoV
DE Verified work portfolio

ProoV Portfolio

Piyush Thakur

Artificial intelligence and Data Science · GGSIPU

View the ProoV leaderboard

Projects

Certified

Self-directed project

Machine Learning for Automotive Safety

Perception Validation Engineer (ADAS Safety Sign-off) · AI / ML · July 2026

92/ 100

A ProoV case study · educational project, not employment

Built a perception validation dossier end to end for a synthetic Aurora-7 detector: defined detection by IoU>=0.5, computed aggregate precision/recall and VRU false-negative rate, and exposed the dangerous night/occlusion slices with per-condition recall analysis. The final recommendation was evidence-based and internally consistent, pairing a daylight-only release with concrete mitigations and a correct comparison to the Uber Tempe crash.

Graded against

  • Detection metrics correctness (precision, recall, VRU false-negative rate)30%
  • Failure-mode analysis & per-condition rigour25%
  • SOTIF safety case quality (ISO 21448 reasoning)25%
  • Ship verdict — evidence-based & internally consistent20%

Passed · pass mark 60/100

What stood out6
  • Computed and interpreted the IoU threshold correctly, including the explicit miss case at IoU 0.111.
  • Reported aggregate precision/recall alongside the VRU false-negative rate and correctly treated VRU recall collapse as the safety issue.
  • Sliced recall by lighting, visibility, and rarity, exposing the severe night (0.39) and night+occluded (0.27) collapse.
  • Wrote a conditional release verdict that cites its own metrics and stays consistent with the daylight-only mitigation.
  • Leakage-Free Detection Definition
  • Safety-Critical Metric Selection
The work I submitted20 tasks

12 tasks · 15.9k characters · Python · 8 written answers · 915 words

  • Sensor Match553 characters
  • Example Iou Demo1.5k characters
  • Task Definition Code1.1k characters
  • Example Metrics DemoPython · 2.2k characters
  • Scored Metrics RunPython · 2.3k characters
  • Scored Metrics351 characters
  • Ttcs Example SlicePython · 1.3k characters
  • Ttcs Triage SlicePython · 1.6k characters
  • Failure Triage1.8k characters
  • Ship Verdict1.4k characters
  • Realcase Analysis976 characters
  • Teachback883 characters
  • Sensor Match27 words
  • Example Iou Demo169 words
  • Task Definition Code149 words
  • Example Metrics Demo154 words
  • Scored Metrics Run143 words
  • Scored Metrics18 words
  • Ttcs Example Slice143 words
  • Ttcs Triage Slice112 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

Machine Learning for Automotive

AI / ML · June 2026

72/ 100

A ProoV case study · educational project, not employment

A verified, self-directed industry project — completed and passed a real industry rubric at 72/100 on ProoV.

Graded against

  • Exploratory Data Analysis20%
  • Feature Engineering25%
  • Model Building & Evaluation35%
  • Business Communication20%

Passed · pass mark 60/100

What stood out6
  • Correctly identified and communicated the Random Forest advantage over Linear Regression using R² and MAE.
  • Derived the required predictive features car_age and mileage_per_year and handled invalid values.
  • Translated model performance into a business impact estimate for a CPO team.
  • Identified the most important pricing drivers and tied them to market intuition.
  • Data-Driven Decision Making
  • Feature Engineering
The work I submitted10 tasks

5 tasks · 6 lines · 5 written answers · 190 words

  • VW Sprint1 Complete56 characters
  • VW Sprint2 Complete61 characters
  • VW Sprint3 Complete59 characters
  • VW Business Insights1.4k characters
  • Jupyterlite Code2 lines
  • VW Sprint1 Complete1 word
  • VW Sprint2 Complete1 word
  • VW Sprint3 Complete1 word
  • VW Business Insights186 words
  • Jupyterlite Code1 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