Dinan Jayasinghe — Portfolio

Projects

Certified

Self-directed project

Machine Learning for Automotive

AI / ML · August 2026

92/ 100

A ProoV case study · educational project, not employment

Built an end-to-end used-car pricing analysis for VW and Audi listings in the UK market. Combined the datasets, engineered predictive features such as car age and mileage-per-year, trained and compared Linear Regression and Random Forest models, and used R²/MAE/RMSE to show the Random Forest as the stronger pricing model. Also produced a business summary that identified the main pricing drivers and recommended deployment for CPO valuation workflows.

Graded against

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

Passed · pass mark 60/100

What stood out6

Combined VW and Audi listings into a single analysis frame with a brand indicator for cross-brand comparison.
Engineered the key predictive features required by the brief, including car age and mileage-per-year, and applied data cleaning for implausible rows.
Compared Linear Regression against Random Forest using R², MAE, and RMSE, then translated the results into a clear CPO pricing recommendation.
Leakage-Free Feature Engineering
Comparative Model Evaluation
Business Translation of ML Results

The work I submitted10 tasks

5 tasks · 6 lines · 5 written answers · 163 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 Insights159 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

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 correctly with an IoU >= 0.5 match rule, computed precision/recall and the VRU false-negative rate, and then sliced recall by lighting, visibility, and class to expose the dangerous night and occluded VRU failures. The final safety case framed these as ISO 21448 functional insufficiencies and closed with an evidence-based GO-WITH-CONDITIONS recommendation tied to the dossier’s own numbers.

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 carried forward the correct IoU threshold rule: a match only counts at IoU >= 0.5, with unmatched real objects treated as false negatives.
Used VRU recall and VRU false-negative rate as the safety metric, explicitly showing why aggregate accuracy is misleading.
Identified the worst slice as night + occluded with recall 0.27 and kept catastrophic VRU misses in the red band.
Wrote concrete mitigations such as daylight-only restriction, sensor-fusion fallback, targeted night/rare-class data, and driver-attention requirements.
Leakage-Free Detection Definition
Safety-Critical Metric Selection

The work I submitted20 tasks

12 tasks · 17.0k characters · Python · 8 written answers · 845 words

Sensor Match553 characters
Example Iou Demo1.5k characters
Task Definition Code1.1k characters
Task Definition377 characters
Example Metrics DemoPython · 2.2k characters
Scored Metrics RunPython · 2.3k characters
Scored Metrics351 characters
Ttcs Example SlicePython · 1.3k characters
Failure Triage1.8k characters
Ttcs Triage SlicePython · 1.6k characters
Sotif Case2.5k characters
Ship Verdict1.5k characters
Sensor Match27 words
Example Iou Demo169 words
Task Definition Code149 words
Task Definition42 words
Example Metrics Demo154 words
Scored Metrics Run143 words
Scored Metrics18 words
Ttcs Example Slice143 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

Predictive Maintenance: Industrial ML for Fault Detection

Condition-Monitoring Engineer · AI / ML · July 2026

92/ 100

A ProoV case study · educational project, not employment

Built an end-to-end rolling-bearing fault detector from vibration data: engineered RMS, kurtosis, crest factor, and envelope-spectrum defect-band energy; localized the fault to the outer race via BPFO; trained a depth-capped decision tree on training bearings only; and evaluated it on held-out bearings with reported catch-rate and false-alarm rate. Also justified an alarm threshold using the candidate’s own cost numbers in a maintenance memo.

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

Computed time-domain features that clearly separate healthy and faulty signals, with kurtosis and crest factor jumping sharply on the impulsive fault.
Used the provided envelope-spectrum helper and correctly found BPFO as the dominant band, mapping it to the outer race.
Kept the classifier compact and interpretable, stating a depth-1 tree with 3 nodes and confirming training-only fitting.
Defended the 0.41 threshold with concrete catch-rate, false-alarm, and euro-cost figures in a maintenance-facing memo.
Leakage-Free Feature Engineering
Honest Model Evaluation

The work I submitted20 tasks

12 tasks · 13 lines · Python · 8 written answers · 501 words

Initial Prediction62 characters
Load Plot Signal CodePython · 1.8k characters
Load Plot Signal205 characters
Example Rms WorkedPython · 697 characters
Time FeaturesPython · 1.9k characters
Fault Location239 characters
Train Classifier363 characters
Evaluation Heldout288 characters
Threshold Decision335 characters
Decision Memo878 characters
Freq FeaturesPython · 1.0k characters
Jupyterlite Code2 lines
Initial Prediction9 words
Load Plot Signal Code163 words
Load Plot Signal15 words
Example Rms Worked72 words
Time Features173 words
Fault Location14 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