Akanksha Tiwari

Project: PostNord (Logistics and Fleet Analytics Platform)

Role: Data Scientist

• Designed Python-based data processing pipelines using Pandas and NumPy to analyze truck utilization, route performance, and operational logistics data.
• Built data cleaning and transformation workflows for large operational datasets to improve accuracy and consistency of logistics analytics.
• Developed REST APIs and WebSocket-based services for streaming real-time operational data, and enabling live monitoring dashboards.
• Implemented data analysis and visualization using Matplotlib and Jupyter Notebook to identify utilization trends and operational inefficiencies.
• Performed exploratory data analysis (EDA) on fleet data to uncover patterns affecting transportation efficiency and delivery delays.
• Integrated analytics services with OpenShift-based microservice environments to enable scalable data processing pipelines.
• Developed SQL queries and ETL workflows to extract logistics data from operational databases, and transform it for analytics reporting.
• Version-controlled data science experiments and pipelines using Git and GitHub.
• Deployed and monitored analytics services on Linux environments, ensuring performance and reliability.

Project: MCX Trading and Banking (Market Data Analytics)

Role: Data Scientist

• Developed Python automation and data processing scripts for analyzing financial trading datasets.
• Built SQL-based analytical queries to extract trading metrics, such as volume trends, transaction patterns, and anomaly detection signals.
• Performed time-series data analysis using Pandas and NumPy to study market activity and trading behavior.
• Conducted data visualization and trend analysis using Matplotlib in Jupyter Notebook to support financial reporting.
• Implemented data transformation pipelines to prepare raw trading data for analytics and reporting workflows.
• Built backend data services using Python APIs to expose processed analytics data to internal reporting systems.
• Used Linux-based environments for script execution, debugging, and large dataset processing.
• Managed deployment pipelines and code versioning using Git and GitHub.

Project: Jaguar Land Rover (Automotive Data Analytics)

Role: Data Scientist

• Developed Python modules using OOP principles to process automotive telemetry and system diagnostic data.
• Built data transformation and feature engineering pipelines using Pandas and NumPy for automotive performance datasets.
• Conducted exploratory data analysis to detect patterns in vehicle performance and system behavior.
• Developed analytical dashboards and visual reports using Matplotlib within Jupyter Notebook.
• Integrated data services with backend APIs, and OpenShift infrastructure for scalable data processing.
• Built SQL queries for extracting and analyzing vehicle data stored in relational databases.
• Used Linux-based development environments for data pipeline execution and testing.
• Maintained the project codebase and experiment tracking using Git and GitHub.

Project: GSK Healthcare (Healthcare Data Analytics & Reporting)

Role: Data Scientist

• Processed and analyzed healthcare claims datasets using Python, Pandas, and SQL to identify reporting metrics and trends.
• Designed data extraction and ETL pipelines to transform healthcare operational data for analytical reporting.
• Performed data cleaning and preprocessing to ensure data quality and accuracy for downstream analytics tasks.
• Built SQL-based reporting queries and dashboards supporting healthcare business intelligence workflows.
• Conducted statistical analysis and visualization using Matplotlib and Jupyter Notebook to highlight healthcare claim trends.
• Automated data analysis scripts running in Linux environments for scheduled reporting tasks.
• Managed source code and collaborative development using Git and GitHub.