Ankan ghosh

Create your portfolio with ProoV
ProoV
DE Verified work portfolio

ProoV Portfolio

Ankan ghosh

Computer science and engineering · Lovely professional university

LinkedIn GitHub
View the ProoV leaderboard

Projects

Certified

Self-directed project

Business & Sponsorships — The FC Barcelona Case

Data Science · July 2026

92/ 100

A ProoV case study · educational project, not employment

Built an end-to-end sponsorship case for FC Barcelona: analyzed the revenue mix, segmented fans by region, selected an awareness-focused target audience for ElectraX, assembled a budget-fit asset package, and evaluated campaign performance against KPIs. The final recommendation was explicit and commercially grounded, with clear caveats about the synthetic dataset and a defined threshold for revisiting the deal.

Graded against

  • Business reasoning & decision quality35%
  • Correct use of data25%
  • Frameworks applied20%
  • Communication & structure20%

Passed · pass mark 55/100

What stood out6
  • Correctly identified commercial revenue as the controllable growth stream and computed the 12% uplift target as €392m.
  • Chose Asia-Pacific for ElectraX using a clear awareness logic: largest segment and highest engagement, even though its per-fan value was lowest.
  • Built a relevant awareness-led package and kept spend within budget at €2.9m of €3.2m.
  • Reported KPI performance with actual-vs-target percentages and clearly isolated content reach as the lagging metric.
  • Leakage-Free Commercial Segmentation
  • Evidence-Based Sponsorship Pricing
The work I submitted18 tasks

10 tasks · 9.8k characters · Python · 8 written answers · 666 words

  • Revenue MixPython · 1.3k characters
  • Revenue Mix Compute320 characters
  • Fan SegmentationPython · 1.0k characters
  • Fan Segmentation Note643 characters
  • Package Builder480 characters
  • Negotiation Simulator487 characters
  • Inbox Responses1.6k characters
  • KPI ScorecardPython · 1.1k characters
  • Mid Season Performance Summary1.2k characters
  • Final Recommendation1.8k characters
  • Revenue Mix101 words
  • Revenue Mix Compute48 words
  • Fan Segmentation53 words
  • Fan Segmentation Note94 words
  • Package Builder41 words
  • Negotiation Simulator69 words
  • Inbox Responses177 words
  • KPI Scorecard83 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 Safety

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

92/ 100

A ProoV case study · educational project, not employment

A verified, self-directed Perception Validation Engineer (ADAS Safety Sign-off) project — completed and passed a real industry rubric at 92/100 on ProoV.

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
  • Correctly established IoU ≥ 0.5 as the detection match threshold and computed the worked example as a miss when IoU = 0.111
  • Computed and interpreted aggregate precision/recall and the VRU false-negative rate correctly from the synthetic table
  • Identified the dangerous slices clearly: night, occluded, and night+occluded VRU conditions with the worst recall at 0.27
  • Wrote concrete SOTIF mitigations tied to specific failure modes, including daylight-only restriction and sensor-fusion fallback
  • Data-Driven Decision Making
  • Safety-Critical Reasoning
The work I submitted20 tasks

12 tasks · 19.9k characters · Python · 8 written answers · 952 words

  • Sensor Match553 characters
  • Task Definition Code1.1k characters
  • Task Definition377 characters
  • Scored Metrics RunPython · 2.3k characters
  • Failure Triage1.8k characters
  • Sotif Case3.7k characters
  • Ship Verdict2.8k characters
  • Realcase Analysis1.5k characters
  • Teachback1.8k characters
  • Example Iou Demo1.5k characters
  • Example Metrics DemoPython · 2.2k characters
  • Scored Metrics351 characters
  • Sensor Match27 words
  • Task Definition Code149 words
  • Task Definition42 words
  • Scored Metrics Run143 words
  • Failure Triage48 words
  • Sotif Case166 words
  • Ship Verdict178 words
  • Realcase Analysis199 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
2Projects completed
2Verified certificates
92Average score
Create your portfolio with ProoV