Anne Charlotte Leysen

As part of a mathematical consultancy team, I created a model to simulate large crowds in public areas during a crisis situation, e.g., an attack or crushing incident.

Detailed OS maps were ingested (from the UK) to create a base landscape of buildings, streets, and pavements. A crowd was spawned onto the map with varying demographics (age, fitness, gender), and various stress responses were simulated for each crowd member, e.g., flight, fight, freeze, hide, etc.

The entire codebase was created with Python and hosted in AWS cloud. A UI/front end was built for users to create new simulations and view simulation results.

We did in-depth, real-world research on crowd behaviors and psychology for each new feature. I was responsible for translating the research into a form that code be coded, and I helped code many of the features implemented in the model.

As part of a team, we created a home hazard model that would predict category-1 hazards in homes across the UK. The hazards we focused on included dampness and mold, excess cold, fire, falls, and electrical.

The training dataset included address-level data on the buildings' construction, e.g., wall material, insulation materials, types of boiler, etc. This was enriched with other data, such as weather and poverty metrics.

We used supervised learning models such as logistic regression, SVM, and a random forest. We also experimented with clustering algorithms and Naive Bayes classifiers. The final outputs included low-, medium-, and high-level risk predictions for thousands of households across the UK.

Created a data platform and automated pipeline from scratch for a financial research company based in London, UK. I hosted a daily data pipeline feed on Azure Cloud using Data Factory and Databricks.

The data pipeline consists of fetching data from various sources via APIs, ingesting it as raw files, processing it through a validation pipeline, and cleansing it into a final processed dataset. I built several dashboards on Power BI based on the data to aid the business in decision-making.

Created time series data pipeline from web scraping sites using Python, such as flight tracking data.

Supported over 200 users in data science and data analytics functions on the AWS SageMaker machine learning platform. I resolved complex problems relating to predictive analytics and visualizations for the Joint BioSecurity Centre in the UK, focusing on COVID-19-related data and situational awareness.

Collaborated in a cross-functional team with engineers and a product manager to define content performance metrics and a supporting data model in Amazon Redshift and produce analysis and self-service dashboards on top of this data, including experiment analysis and tracking dashboards.

My responsibilities included refining and validating the supporting data model in Amazon Redshift. I used SQL to explore data and identify necessary changes, collaborating with engineers to implement changes.

I also defined performance metrics based on exploratory data analysis, product considerations, and statistical power analysis, such as tweaking metric definitions to allow A/B tests to run faster. I built self-service experiment analysis and metric tracking dashboards using SQL and Python in a Sisense visualization product.

Focused on data analytics and data science in search engine marketing and SEO for Hotels.com at Expedia.

I challenged digital marketing strategies and improved growth by running incrementality tests such as pre- and post-testing, A/B testing, and time series modeling. I also found opportunities for collaboration between the Expedia brands to leverage our combined market share. I used various modeling techniques in R and Python, data preparation in SQL, and data visualization using Tableau and Qlik Sense.

An online marketplace, eCommerce website, and iOS app focused on selling creative workshops and experiences.

I co-founded and built the website and back end to run the platform entirely and automatically. The platform grew to over 10,000 users in the 1st year and registered over 200 partners.

Conducted a three-week analysis on churn rates of a monthly subscription-based product. I brought together multiple data sources spread across 3rd-party data integration platforms and internal data warehouses, including ChartMogul, Amplitude, and Amazon Redshift.

I also explored key drivers of user cancellations, including user demographics, properties, and behaviors. I built a pipeline to assess feature importance using an XGBoost model. I produced graphical charts to analyze patterns and correlations across cancellation rates and features. Finally, I leveraged ChartMogul's churn rate calculations regarding the customer, net MRR, and gross MRR to build a coherent story around the development of the churn rate over time.

Developed tools to calculate marketing attribution across channels, such as search engine marketing, brand, programmatic ads, and direct. I incorporated seasonality as a separate model to improve the estimation. The tools were used to allocate marketing capital each quarter.

To improve hospital capacity management, our team developed a predictive model to identify how long a new patient at a hospital would likely need to spend in a hospital bed. This would be based on the patients' initial screening metrics and demographics, such as blood pressure and cholesterol levels. This project was part of a "Health Hackathon" where doctors came together with data scientists and jointly developed a solution.