ITACADEMYprojectes/ProjecteData
Nov 2024 – Dec 2024
2 Months active
Languages Used
Jupyter NotebookPythonSQLCSVPower BI
Technical Skills
Data AnalysisData VisualizationJupyter NotebookKPI TrackingMatplotlibPandas
ITACADEMYprojectes/ProjecteData
PROFILE
Itacademyprojectes/projectedata
During two months on ITACADEMYprojectes/ProjecteData, Marc Costa delivered six features focused on marketing analytics and customer profiling. He developed Jupyter Notebook-based workflows for KPI tracking, client segmentation, and product propensity analysis, leveraging Python, Pandas, and Scikit-learn. His work included building data pipelines for Power BI integration, implementing PCA and K-Means clustering for segmentation, and ensuring data quality through cleaning and export management. By validating data paths and maintaining repository hygiene, Marc enabled reproducible analytics and reliable dashboards. The depth of his contributions provided actionable insights for targeted marketing, supporting data-driven decision making without requiring major bug remediation.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
23Total
Bugs
0
Commits
23
Features
6
Lines of code
133,200
Activity Months2
Your Network
36 people
Work History
December 2024
15 Commits • 3 Features
Dec 1, 2024Month: 2024-12 | Repository: ITACADEMYprojectes/ProjecteData. Focused on delivering end-to-end analytics for marketing effectiveness and customer profiling, with robust data assets and pipelines to enable BI and data-driven decision making. Key data quality improvements and cleanup to ensure reliable dashboards and reports. Sprint-aligned work completed across KPI analysis, segmentation, propensity analysis, and data preparation artifacts.
15 Commits • 3 Features
Dec 1, 2024Month: 2024-12 | Repository: ITACADEMYprojectes/ProjecteData. Focused on delivering end-to-end analytics for marketing effectiveness and customer profiling, with robust data assets and pipelines to enable BI and data-driven decision making. Key data quality improvements and cleanup to ensure reliable dashboards and reports. Sprint-aligned work completed across KPI analysis, segmentation, propensity analysis, and data preparation artifacts.
December 2024
November 2024
8 Commits • 3 Features
Nov 1, 2024November 2024 performance summary for ITACADEMYprojectes/ProjecteData: Delivered three core features across the repository: (1) test scaffolding creation and cleanup to validate setup and teardown processes, (2) advanced client analytics notebooks with profiling visuals for demographics and product uptake, and (3) KPIs notebook for bank marketing metrics including deposits conversion, call metrics, and interaction analyses. Minor cleanup and file removals accompanied scaffolding work. No major bugs fixed this month; focus was on delivery, validation, and quality improvements. Overall impact: enabled reliable validation workflows, richer client insights, and improved marketing analytics readiness, accelerating data-driven decision making. Technologies and skills demonstrated: notebook-based analytics, data visualization, data-path validation, and Git-based collaboration across a data science workflow.
November 2024
8 Commits • 3 Features
Nov 1, 2024November 2024 performance summary for ITACADEMYprojectes/ProjecteData: Delivered three core features across the repository: (1) test scaffolding creation and cleanup to validate setup and teardown processes, (2) advanced client analytics notebooks with profiling visuals for demographics and product uptake, and (3) KPIs notebook for bank marketing metrics including deposits conversion, call metrics, and interaction analyses. Minor cleanup and file removals accompanied scaffolding work. No major bugs fixed this month; focus was on delivery, validation, and quality improvements. Overall impact: enabled reliable validation workflows, richer client insights, and improved marketing analytics readiness, accelerating data-driven decision making. Technologies and skills demonstrated: notebook-based analytics, data visualization, data-path validation, and Git-based collaboration across a data science workflow.
Activity
Loading activity data...
Quality Metrics
Correctness86.2%
Maintainability86.2%
Architecture83.4%
Performance82.6%
AI Usage22.6%
Skills & Technologies
Programming Languages
CSVJupyter NotebookPower BIPythonSQL
Technical Skills
Business IntelligenceClusteringData AnalysisData CleaningData EngineeringData ExportData PreprocessingData ProcessingData VisualizationExploratory Data Analysis (EDA)Feature EngineeringFile ManagementJupyter NotebookKPI TrackingMachine Learning
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline