Hands-on manager and active technical contributor for a Data Science team delivering business solutions in Revenue Management. The team is leveraging enterprise-level AI to create scalable, machine-learning solutions. Current focus areas are:* Pricing Automation: Enhancing pricing logic to make superior and more nuanced pricing recommendations at granular-levels by employing hierarchical time-series methods to combat intermittent demand effects and incorporate brand-wide trends. * AB Testing: Working with Revenue Management to develop a rigorous framework to design and execute successful AB testing with small-sample sizes. Tools include power analysis, matched-pair design, sample clustering, significance testing, and other quantitative methods.

• Forecasting Onboard Revenue: Developed a model that accurately forecasts the overall onboard spending of sailings. • Inventory Optimization: Developed and released a novel optimization model, powered by an Azure Data Factory/DataBricks/Spark pipeline, to help Revenue Management product teams more evenly pace sales of cabin inventory across substitutable sailings. • Forecasting Retentions: Designed a new guest-level retention classifier with a substantial improvement in accuracy over the production model. • A/B Pricing Experiments: Worked with an analytics team that assisted RCI's product managers in designing and executing pricing experiments through power analysis calculations and other supporting analysis.

•Demand Forecasting Model: Refitted Revenue Management’s cabin price recommendation engine with an improved demand forecast to significantly improve improve the engine's pricing recommendations. The new demand forecast relies on a hybrid forecasting model combining a historical forecast with univariate time-series models. • COVID-19 Risk Assessment: Assessed the risk of infected passengers boarding cruise ships, which included forecasting infection rates for known demographic profiles by using regression and compartmental epidemiological models. This work was directly presented to executive members, including the CEOs of the Royal Caribbean Group and Royal Caribbean International.

Led and assisted scientific investigations in David Fitzpatrick's laboratory to acquire and analyze large unstructured datasets of neural activity, including imaging and time-series data: •Analysis routinely included correlation-based approaches, generalized linear models, machine learning, and clustering/dimensionality reduction techniques to uncover how developing neural circuits process and probabilistically encode information about sensory stimuli.•Image processing and segmentation pipelines to extract neural responses from unstructured imaging data. These tools are employed by other scientists at the Institute and scientific community at large. Worked closely with other lab members on scientific projects and championed employing state-of-the-art analytics in Python/MATLAB. •Translated basic science into theoretical models. Collaborated with a German computational neuroscience group on data analysis and theoretical modeling about neural circuit development (2013-Present). • Promoted to Research Scientist from Postdoctoral Scientist in 2018, in recognition of scientific contributions and voluntary teaching roles.• Published four peer-reviewed papers at prestigious scientific journals. Presented research to a director from Microsoft Research (2019) and at other major scientific conferences: Society for Neuroscience (2014-2018) / Cosyne (2016-2017), 2016 Cell Meeting: Big Questions in Neuroscience, and 2017 Vision Sciences Society.Advanced the Max Planck Florida Institute's business outreach in Neuroscience and Data Science:•Regularly presented research to other scientists, the public, and the business community.•Mentored a FAU Master's student in Data Science (2019-Present).•Hosted an imaging analysis workshop for the Neuroimaging course (2017-2019).•Taught a monthly data science workshop using Python/Matlab to other scientists (2016-2018) , which became the basis for future educational outreach programs at the Institute for Machine Learning & AI.

•Carried out a collaborative dissertation project involving three separate laboratories (Justin Crowley at Carnegie Mellon University, Seong-gi Kim at University of Pittsburgh, and Fred Wolf at the Max Planck Institute for Dynamics and Self-Organization) to study how the emergent functional organization of developing neural circuits is perturbed by structural alterations of the developing brain. •Acquired and analyzed large unstructured datasets of neural activity, including imaging and time-series data. Used MATLAB to develop quantitative tools, such as automatic cell segmentation methods, Fourier filtering, and wavelet transforms, to detect subtle changes in the spatial organization of neural maps as a function of normal aging.•Published a peer-reviewed publication and presented research at major conferences: Society for Neuroscience (2010-2012) and 2012 Gordon Research Conference. • Teaching assistant for the Multimodal Neuroimaging Training Program (2010).

•Programmed a stochastic kinetic simulation of capsid formation during virus self-assembly using Java (Spring 2007 - Chemistry Senior Research Project with Dr. David Wu) •Carried out a one-year design project focusing on the evaporative droplet reduction of Kα x-ray point sources with a CO2 laser (2006 - Engineering Physics Senior Design Project with Dr. Charles Durfee) •Verified mathematical theory behind composite diffracted evanescent waves with computational methods (Summer 2005 - Research Experience for Undergraduates with Dr. Reuben Collins) • Designed photon counting, time delay, and amplifier circuits in an ultra-fast optics laboratory environment (Summer 2004 - Independent research project with Dr. Jeff Squier)

•Automated the setup and data acquisition for a quantum version of Optical Coherence Tomography using Matlab (Summer 2006 - Research Experience for Undergraduates with Dr. Malvin Teich)