Profile

Machine learning engineer building auditable decision systems for noisy, multi-source data

I build machine-learning and analytical systems for noisy, incomplete fast-moving data.
My work focuses on market intelligence, anomaly detection and probabilistic decision system reliability. The common theme is turning unstable signals into reasons that can be inspected before it is trusted.

My independent portfolio is organised around 3 core areas: market intelligence, reliability monitoring and real world infrastructure.
The wider direction is evidence-led audits across crypto, property and AI infrastructure: testing what supports a claim, what weakens it, what is missing and what should be checked next.

core focus

Quantiative Applied ML for risk analytics

Machine Learning Engineering

Building analytical pipelines, scoring workflows and model-backed systems for noisy, changing or incomplete data environments.

Risk Analytics & Monitoring

Testing uncertainty, instability, anomalies and failure points before model outputs are used in operational or financial decisions.

Quant Analytics

Applying probabilistic modelling, signal analysis and diagnostic evidence chains to markets, risk and decision systems.

Technical ownership

Evidence-led systems: from noisy data to inspectable decision output

National-scale geospatial ML diagnostics

Built a reproducible cross-domain analytical framework across 23,951 grid cells on a 25 km national raster, integrating manufacturing, infrastructure, port-accessibility and satellite-derived features.

Methods: PCA, UMAP, HDBSCAN, ARI, local concordance, bootstrap stability, Moran's I and LISA.

View research →

Reliability testing and uncertainty diagnostics

Tested whether learned structures were stable, locally consistent and decision-useful before treating them as evidence.

Measured output: 10 repeated UMAP seeds, 25 bootstrap runs per method, 300 pairwise ARI comparisons, 999 Moran permutations and 499 LISA permutations.

View projects →

Auditable decision evidence

Converted model disagreement into outputs that can be inspected through maps, metrics, filters, dashboards, tooltips and cell-level evidence trails.

Measured output: UMAP produced 9 clusters with 93.6% mean local stability; PCA produced 10 clusters with 38.8% noise; satellite clustering produced 3 clusters with 65.5% noise.

Experience

Technical portfolio, property, web systems and regulated finance

A compact view of the work behind my independent portfolio, supported by property, commercial and financial-services experience.

Founding Machine Learning Engineer (2021–Present)

Kian Info - Independent ML Engineering Portfolio

Independent ML engineering portfolio focused on noisy data, market intelligence, anomaly detection and probabilistic decision systems.

  • Realtime Market Intelligence GCP: monitored 5 networks, ~230,000 pair/pool sources, 12-second updates and ~160M batched contract calls per day.
  • Geospatial ML Diagnostics: analysed 23,951 grid cells on a 25km raster using PCA, UMAP, HDBSCAN, ARI, bootstrap stability, Moran’s I and LISA.
  • State Space Anomaly Detection: built sequential anomaly-detection logic for hidden-state change, instability and abnormal behaviour in noisy time-series data.

Focus: Navigating uncertainty, market intelligence, anomaly detection, geospatial ML, probabilistic systems.

Property Development & Operations (2024-2025)

Private Property Asset Project

Led a private residential property project across acquisition, financing, contractor coordination, compliance, cost control and operational optimisation.

  • Managed a £30k+ improvement budget.
  • Improved asset value from £100k+ to £170k+ GDV.
  • Achieved £25k+ annual gross rental yield.

Focus: asset risk, yield, constraints, operational management.

Web Developer (2023-2024)

Independent Web Systems Business

Built and delivered web systems for local businesses, covering prototyping, implementation, deployment, client communication and support.

  • Developed ~6 custom prototypes from ~750 local businesses.
  • Converted ~4 of 18 active prospects into paid work.
  • Generated ~£2,450 initial project revenue.
  • Built recurring support interest from 3 clients.

Focus: technical delivery, outreach, client work, commercial execution.

Property Operations (2023)

UK Luxury Real Estate Brokerage

Supported client acquisition, property operations, listings and sales-process activity in a luxury real estate environment.

  • Networked with ~40 new people per week across 2 weekly events.
  • Handled ~30 calls per week and attended ~2-3 client meetings per week.
  • Secured ~£8.3M in listings across 5 vendors relationships, representing an estimated ~£250k commission pipeline for the company.

Focus: property markets, sales pipeline, networking, client handling.

Customer Service Representative (2022)

UK Retail Bank

Worked in a regulated financial-services environment handling customer transactions and compliance-bound account operations.

  • Served ~60 customers per day on average.
  • Built exposure to operational risk, financial controls and transaction processes.
  • Worked accurately under high-volume service constraints.

Focus: regulated finance, transaction handling, service risk, financial controls.

Skills

Capability stack

ML and statistical modelling

Probabilistic modelling Bayesian inference State-space modelling Time-series modelling Dimensionality reduction Clustering

Reliability and monitoring

Anomaly detection Reliability analysis System monitoring Temporal drift Bootstrap stability Decision support

Engineering and delivery

Python SQL FastAPI NumPy Pandas GeoPandas OpenCV scikit-learn TensorFlow GCP API integration Linux/Unix CLI