• Assist with the development and optimization of models estimating key elements of brand performance, including the similarity and difference of advertisement images, video and text, revenue and financial modeling, clustering and processing audience discussion of brands, and modeling the relative importance of metrics in overall brand health. • Assist with the production and delivery of analyses to current customers, including QA of the work of junior resources, independent supplementary analysis to our core deliverable, and performing custom analyses on topics of special interest to larger customers. • Act as a supplementary technical resource on client calls and sales calls, to answer questions and walk through our methods around the collection, processing, distillation, and presentation of data. • Research and leverage data collection systems and other strategies to collect information on brand performance • Develop fast or automated processes to collect and process data relevant to brand performance. • Manage BlueOcean processes for the collection, processing, delivery and presentation of brand performance data • Create written communication materials that effectively document models and data collection processes and make recommendations regarding opportunities for improvement. • Conduct the full lifecycle of analytics projects, including pulling, manipulating, and exporting data from project requirements documentation to design and execution • Evaluate key BlueOcean performance indicators, provide ongoing reports, and recommend business plan updates

• Innovate and improve machine learning models • Design, develop, and deploy machine learning models to solve problems • Partner with business leaders and technical experts to develop new data sources • Improve modeling methodology and apply models with sound risk management

• Innovate and improve machine learning models • Design, develop, and deploy machine learning models • Partner with business leaders and technical experts to develop new data sources • Improve modeling methodology and apply models with sound risk management

• Improve existing supervised fraud detection models (primarily XGBoost) through feature engineering, tuning, and evaluation • Design and implement unsupervised and semi-supervised anomaly detection models (e.g., ECOD, Isolation Forest, clustering-based approaches) • Explore ensemble strategies combining anomaly signals, supervised scores, and business rules • Analyze fraud patterns in FNOL (First Notice of Loss) and downstream claim lifecycle data • Develop new model concepts for emerging fraud patterns (temporal anomalies, behavior shifts, structural inconsistencies) • Evaluate bias, stability, and confidence of fraud scores and support threshold calibration • Partner with engineering to productionize models in AWS + Snowflake environments • Support customer-facing analysis and explanations, including Japanese-language discussions when needed • Document findings, assumptions, and tradeoffs clearly for technical and non-technical audiences