shenderov

Working as part of Cross-sell marketing team. Leading a group of one junior and one middle data analyst within the Annuity department; Designing and validating A/B tests with manager teams and Analytics team-leads; Conducting A/B tests and assessing the results, providing business insights based on the conclusion; Setting up automatic monitoring of A/B tests for the whole Cross-sell team, including messenger notification with current status changes and early warnings; Gathering analytics on how the marketing campaigns and A/B test are going, including coverage metrics and lead funnels; Finding optimal metrics for different products and solving the dilemma of effectively measuring the overall effect on multiple competing products.

Working with the marketing team to analyze the lead flow. Collecting information on incoming leads and stats of how and when they have been processed (MySQL + Python); Building dashboards to monitor lead conversion funnel (Tableau); Building views in SQL for further Tableau visualization; Analysing key marketing metrics for the product and introducing new ones; Improving visualisation through better suited metrics or correcting parameters within dashboards; Rapid hypothesis testing, and on-the-go analysis; Scripts and views transfers and optimisation through Snowflake; Working remotely with LA team, having 15hrs time diff.

Project 2 (DS, current): Satellite imagery processing. Different providers (api calls). Histogram matching, extracting coordinates and metadata (Gdal). Coordinate re-/referencing images(Qgis); NN re-training. Building custom data transforms for input imagery (PyTorch); Optimization of Skimage histogram-matching for best performance in defined conditions; Using NumPy vector operations to boost performance of image pre-processing; Working with time-series data, building classification models (Sklearn and boosting); Exploring possible extensions for the product, searching how to solve potential clients’ business need. Project 1 (DE): Creating and maintaining ETL/ELT pipelines for the client; Processing various types of data: Tables/Text/Imagery; Building data processing pipelines with PySpark; CI/CD development; Working within SCRUM-environment.

Working with raw data from Oil&Gas companies. Filtering results, merging large datasets extracted from multiple sources(.xls files, .las files, etc.). Processing time-series data, including its visualization and validity check. Anonymization of client data for 3rd party processing (pandas, sci-py, signal processing); Building custom functions based on requirements for the current task; Analysing and processing time-series data, generating additional statistical features, data discretisation and feature extraction; Preparing the pipeline for algorithm testing within clients work flow; Co-designing the user-interface for the final software in ‘Figma’ with UI/UX contractors; Preparation of reports for each of the project steps, formulating key goals, achieved by the team.