Victoria Zhou

Victoria Zhou

Lead Data Scientist
United Kingdom

About Me

Lead Data Scientist with experience in ESG data, LLM-based projects, and data science with big data. Has worked on topic modelling, prompt generation, sustainable finance data frameworks, scoring frameworks, emission ext…

Experience

Lead Data Scientist

HSBC, London
Mar 2022 - Present · 4 years 4 months

Lead the topic modelling project for global banking.
Analysed information obtained from channels including Slido to provide insights on the focuses of the questions raised.
Worked on a prompt generation project involving instruction tuning LLM so that the model could generate quality questions.
Fed the generated questions into LLM in order to obtain quality answers.
Worked on HSBC’s sustainable finance data framework involving vendor engagement and feasibility analysis.
Analysed data coverage within geography and sector to recommend vendor data acquisition.
Transformed data to form a foundational generic data asset with coverage for HSBC clients.
Created a taxonomy that deduplicated and standardised data points across different vendors.
Pod lead and lead data scientist for developing the sustainable scoring framework for wholesale banking.
Leveraged the ESG data asset to help provide scores across all three pillars including aggregations across sectors and geographies.
Pod lead and lead data scientist for developing the emission extrapolation for wholesale banking.
Built a regression model using public clients’ sustainability information.
Used the model to make predictions for private HSBC clients.

Lead Data Scientist

HSBC
Jul 2019 - Present · 6 years 11 months

Lead the topic modeling project for global banking. The project involves analyzing information obtained from channels including Slido to help provide insights on what are the focus of the questions raised.

Worked on prompt generation project which involved instruction tuning LLM so that the model could generate quality questions. The questions are then fed into LLM in order to obtain quality answers. The downstream users would be the relationship managers.

Worked on HSBC’s sustainable finance data framework which involved vendor engagement and feasibility analysis, data coverage within geography and sector to recommend vendor data acquisition. This was then analyzed and transformed to form a foundational generic data asset that provided coverage for HSBC clients with a taxonomy that deduplicated and standardized data points across different vendors.

Pod lead and lead data scientist for developing the sustainable scoring framework for wholesale banking. The methodology involves leveraging the ESG data asset to help provide scores across all three pillars including aggregations across sectors and geographies.

Pod lead and lead data scientist for developing the emission extrapolation for wholesale banking.
The project involves building a regression model using public clients’ sustainability information and the model is then utilized to make predictions for private HSBC clients.

Lead Data Scientist

HSBC, London
Mar 2022 - Present · 4 years 4 months

Lead the topic modelling project for global banking.
Worked on prompt generation project which involved instruction tuning LLM so that the model could generate quality questions.
Worked on HSBC’s sustainable finance data framework which involved vendor engagement and feasibility analysis.
Pod lead and lead data scientist for developing the sustainable scoring framework for wholesale banking.
Pod lead and lead data scientist for developing the emission extrapolation for wholesale banking.

Data Scientist and Engineer

HSBC, London
Jul 2019 - Jan 2022 · 2 years 6 months

Built a clustering model to derive user archetypes for HSBC’s clients.
Built a product recommendation extension of the model using an autoencoder-based architecture to recommend the next best product based on cluster product composition.
Worked in collaboration with a consultancy in a large-scale frontline enhancement project.
Built data pipelines in Kedro to have consistent ETLs for feature engineering.
Built a collaborative feature store creating reusable feature assets derived from HSBC’s internal data.
Enabled machine learning models to access quality-controlled data points.
Worked on various EDA-based projects to analyse HSBC’s internal assets.
Developed relevant features for credit risk modelling.
Conducted in-depth sector analysis useful during the pandemic for supply chain risk analysis.
Worked on the automation of HSBC’s KYC program.
Leveraged big data architectures built on Scala and Hadoop frameworks.
Led the 2020 internship program for HSBC with great feedback.
Managed and led micro-intern projects for the year 2021.
Participated and led R&D development days with the team.
Presented learnings in bull sessions across London and Toronto.

Product Coordinator

CKO International, London, Car Accessories Retailer
Mar 2018 - Jun 2019 · 1 year 3 months

Worked on collaboration and negotiation with relevant manufacturers.
Managed and updated the computerised internal stock system (Octopus).

Client Liaison Officer

Acumedic Ltd., London, Chinese Clinic and Tea Retailer
Apr 2016 - Jan 2018 · 1 year 9 months

Managed cross-country product shipments.

Gap, Cornwall, UK, Tier 2 Dependant Visa
Dec 2014 - Sep 2015 · 9 months

Moved from Shanghai, China to Cornwall, UK in Jan 2015.
Prepared applications to different universities for Masters in Law up to Mar 2015.
Made the decision to study Graduate Diploma in Law with BPP in Apr 2015.
Sent numerous applications for Training Contract from Apr 2015 to Sept 2015.

Ship Operator & Legal Representative

Greatwin Carrier, Shanghai, Shipping
Jul 2013 - Nov 2014 · 1 year 4 months

Handled ships’ operations including loading, unloading and bunkering.
Managed disputes through investigation, analysis and resolution.
Proof-read and prepared charter party contracts.

Data Scientist and Engineer

HSBC, London
Jul 2019 - Jan 2022 · 2 years 6 months

Built clustering model to derive user archetypes for HSBC’s clients.
Built a collaborative feature store that involves creating reusable feature assets derived from HSBC’s internal data.
Worked on various EDA based projects to analyse HSBC’s internal assets.
Worked on the automation of HSBC’s KYC program.
Led the 2020 internship program for HSBC and currently managing and leading micro-intern projects for the year 2021.
Participated and lead R&D development days with the team and present learnings in bull sessions across London and Toronto.

Product Coordinator

CKO International, London
Mar 2018 - Jun 2019 · 1 year 3 months

Worked on collaboration and negotiation with relevant manufacturers.
Managed/updated computerised internal stock system (Octopus).

Client Liaison Officer

Acumedic Ltd., London
Apr 2016 - Jan 2018 · 1 year 9 months

Managerial experience with cross-country product shipments.

Ship Operator & Legal Representative

Greatwin Carrier, Shanghai
Jul 2013 - Nov 2014 · 1 year 4 months

Handling ships’ operations including loading, unloading and bunkering.
Dispute management (investigation, analysis and resolution).
Proof-reading and preparing charter party contracts.

Skills

Python Data Science Google Cloud Platform Google Earth Hadoop Machine Learning Algorithms PySpark Scala TensorFlow Spark Hive Version Control (Git) Linux Anaconda Pandas Numpy ScikitLearn Matplotlib Seaborn Java TensorFlow Git NumPy Scikit-learn SQL Kedro Machine Learning Deep Learning Data Engineering Feature Engineering Clustering Autoencoder Regression EDA Prompt Generation Topic Modelling LLM Vendor Engagement Feasibility Analysis Data Asset Building Taxonomy Data Pipelines ETL KYC Project Management Leadership
Report this Profile?