First and Last Name Toronto, Ontario | www.linkedin.com/in/firstlastname/ | xxx-xxxx-xxxx | email@gmail.com WORK EXPERIENCE DATA SCIENTIST | ACTUARIAL ANALYST July 2022- Present Big name insurance Company Toronto, ON ● Built decision trees incorporating transfer learning techniques to optimize the pricing algorithm of commercial insurance products with XGBoost, leading to an estimated 7% increase in annual revenue ● Developed an automated tool to create visualizations using Shell Scripting and Python , improving efficiency by 71% and reducing error rate. ● Translate business needs into analytical frameworks and present project results and data-driven recommendations to stakeholders from various technical backgrounds. ● Coached 3 new hires throughout projects and built documentation for processes and methodologies used. ACTUARIAL ANALYST INTERN September 2021- December 2021 Same Big name insurance Company as above Toronto, ON ● Sourced and cleaned customer application datasets to implement a gradient-boosting model for fraud detection using Pandas, NumPy and Scikit-learn , which resulted in a 14% increase in fraud detection ● Developed a K-means clustering algorithm to segment customer base and determine an optimal pricing strategy which led to an increase of $125k in annual revenue ● Compiled and analyzed customer retention data using SAS and presented key insights to stakeholders each month. DATA SCIENTIST INTERN May 2021- August 2021 Another insurance company Toronto, ON ● Built and deployed ETL data pipelines to process semi-structured data from 4 different sources to a centralized SQL database using Pandas and NumPy , ensuring flawless integration with existing data pipelines. ● Automated and owned several monthly reporting processes using Python and SQL , saving 60+ hours of manual work each month. ● Implemented bot email alerts to provide updates on automated processes to stakeholders regularly. EDUCATION Big name university ON Bachelor of Mathematics; Honours Statistics (Co-op) September 2017- April 2022 PROJECTS “Pawpularity” of Pet Images using Neural Networks Trained a Convolutional Neural Network using Tensorflow Keras to predict the “pawpularity” scores of pet images, providing accurate recommendations to help pets in shelters find their forever homes. A/B testing- Netflix home-page Optimization Decreased browsing time of Netflix users by 23% through experimental design , factor screening, and Response Surface Methodology. Predicting insurance claims using Logistic Regression Used logistic regression models to predict the likelihood of an insurance claim occurring using R and generated impactful visualizations with ggplot2 TECHNICAL SKILLS Extensive knowledge of descriptive and inferential statistics, machine-learning algorithms, end-to-end model development and validation techniques Experience with Agile Methodology and Git Supervised learning: linear and logistic regression, decision trees, neural networks, support vector machines (SVM) Unsupervised learning: principal component analysis (PCA), K-means clustering Languages: Python (NumPy, Pandas, Scikit-learn, Keras, TensorFlow), R (tidyr, tidyverse, dplyr), SQL, SAS, Matlab Data visualization : Power BI, ggplot2, matplotlib