Danish Mehra
London,LND
Summary
Experienced Data Scientist with a proven track record of delivering end-to-end machine learning solutions that drive measurable business impact across healthcare, finance, retail, energy, and technology sectors. Skilled in collaborative problem-solving, agile project delivery, and rapid prototyping of MVPs informed by user insights. Expertise spans the full data science lifecycle — from defining strategic objectives and designing scalable architectures to developing, deploying, and integrating AI products within business workflows. Proficient in Python, SQL, and cloud platforms (AWS, Azure), with strong foundations in predictive modelling, quantitative analytics, and production-grade ML engineering. Known for bridging technical and business domains, mentoring teams, and applying data-driven strategies to enhance customer engagement, retention, and growth.
Overview
5
5
years of professional experience
Work History
Senior Data Scientist
Notting Hill Genesis
11.2023 - Current
- Designed and deployed an end-to-end disrepair risk assessment model on Azure ML Studio, combining sequence-based temporal models (repairs, complaints, visits) with feature embeddings for property and tenant data. The tool reduced disrepair cases by 30%, with a projected annual saving of £3.3M, and became the company’s flagship predictive risk solution.
- Delivered an image-based damage assessment system leveraging RAG (retrieval-augmented generation) to match new cases with historical inspection data. This AI-driven solution automated manual assessment workflows, reducing inspection time and costs across the organisation.
- Joined as the company’s first and only Data Scientist (~3,000 employees) and built the data science function from the ground up — giving strategic guidance, establishing best practices, scalable ML pipelines, and governance frameworks, and growing the team into a fully functional data science unit.
- Led all data science initiatives across the organisation, providing technical guidance and mentorship to data scientists, analysts, and engineers across multiple business functions. Partnered with engineering, DevOps, analytics, and senior business leaders to ensure end-to-end delivery of robust, production-ready ML solutions.
- Developed a complaint categorisation model using pre-trained transformer embeddings on textual data (call transcripts, complaint descriptions, and responses) to identify root causes of service failure and create feedback loops improving upstream service quality.
- Led customer behaviour and sentiment analysis initiatives to predict churn and recommend next best actions for customer engagement and satisfaction improvement — helping shape customer experience strategies across teams.
Data Scientist
Arca Blanca
09.2021 - 10.2023
- Led the development of a data-driven stocking strategy for a global pharmaceutical client using customer segmentation models and multimodal healthcare datasets. Managed the entire lifecycle — from conception to scalable deployment on AWS — driving a £5M profit increase, 5% stock reduction, and a multi-billion-pound uplift in turnover, while also reducing carbon footprint through optimised logistics.
- Collaborated on a reinforcement learning–based marketing optimisation framework integrating telemetry, marketing, Google Trends, and macro-economic datasets for a cyber-security company, boosting customer lifetime value and reducing churn, leading to a 10% improvement in ROAS.
- Co-developed a deep learning model using transfer learning to predict optimal new site locations for a major retirement housing provider. Delivered a 25% boost in new customer activity and achieved a 10× ROI, demonstrating scalable AI deployment for business growth.
- Partnered with data scientists, engineers, and consultants to design a pricing optimisation forecasting model for a leading retailer, combining market trends, demand patterns, and A/B testing insights — improving revenue margins by 15%.
- Implemented an end-to-end OCR and NLP pipeline for a global energy trading firm, deploying the system on AWS Lambda for document automation. Enhanced OCR accuracy by 20% and processing speed by 30% through benchmarking and integration of Hugging Face models for named entity recognition.
- Conducted global statistical market research for an automotive reseller across 18 international markets, producing insights that guided their transition to net-zero emissions and the forecasting of resale car prices using advanced time-series models (Temporal Fusion Transformers).
Technical Trainer
Purple Beard Training
12.2020 - 09.2021
- Designed and delivered immersive data analysis bootcamps, teaching Applied Statistics, Computer Science fundamentals, and Python-based analytics — including data cleaning, visualization, and machine learning techniques.
- Trained and mentored diverse cohorts of aspiring data professionals, strengthening their skills in model design, statistical testing, and performance evaluation for real-world data challenges.
- Led workshops achieving a 68% post-bootcamp job placement rate across technology, finance, and healthcare sectors, empowering graduates to transition into data-driven roles with confidence.
Education
Master of Science - Big Data Science
Queen Mary University of London
London, ENG08.2021
Bachelor in Technology - Electrical and Electronics Engineering
Shiv Nadar University
Delhi, India08.2020
Skills
- Programming Languages (Python, R)
- Databases and Data Warehousing (NoSQL, MySQL, MongoDB, Google BigQuery, S3, Redshift, Snowflake, Athena)
- Natural Language Processing (NLP)
- Machine Learning Algorithms (Classification, Regression, Dimensionality Reduction, Reinforcement Learning, Time Series Analysis)
- Deep Learning Frameworks (Hugging Face, TensorFlow, Pytorch, Keras)
- Cloud Platforms (AWS, GCP and Microsoft Azure)
- Data Mining and Data Manipulation: (cleaning, indexing, sorting, and transforming data (NumPy, Pandas, Polars, NLTK, Spacy, Scikit-Learn, SciPy, BeautifulSoup, Altair, OpenCV)
- Software Engineering Principles (Git, typing, TDD, structured coding, object oriented programming)
- Statistical Knowledge (Probability, Hypothesis Testing, A/B testing, quasi-experimentation and causal inference)
- Big Data Tools (Spark, Cassandra, Amazon EMR, Hadoop Map Reduce)
- Rest APIs
- Deployment Tools (Docker, MLFlow, AWS Studio, Kubernetes, Lambda, Azure ML Studio, Databricks)
- Data Visualisation Tools (Power BI, Tableau, Looker)
- Enthusiastic towards solving problems through creative innovation promoting modern AI tools and new technologies
- Excellent Storytelling skills to interpret complex solutions into compelling narratives for technical and non-technical audiences
- Collaboration within cross-functional teams
- Adept at writing clean, efficient and production-ready code
- Focused on sharing and setting up best practices to ensure an inclusive learning culture
- Exceptional verbal and written communication skills, coupled with strong interpersonal abilities
- Confident in full autonomy
- Pragmatic problem-solving skills by balancing and prioritizing tasks based on their potential business impact and managing risks
Websites
Languages
English
Timeline
Senior Data Scientist
Notting Hill Genesis
11.2023 - Current
Data Scientist
Arca Blanca
09.2021 - 10.2023
Technical Trainer
Purple Beard Training
12.2020 - 09.2021
Master of Science - Big Data Science
Queen Mary University of London
Bachelor in Technology - Electrical and Electronics Engineering
Shiv Nadar University