Development of Sales and Controlling Dashboards over multiple sales and marketing channels in Power BI
Modelling data schema for efficient data storage
Building Data Pipelines and connectors to REST-APIs with Databricks and Python for data provisioning from different sources
Azure Data Factory for orchestration and scheduling of data ingestion jobs
Implementing Business Logic and visualizing various KPIs in Power BI Dashboards for eCommerce (Procurement costs, delivery costs, retour costs, shop fees etc.)
Data Transformation and cleaning
Leveraged Azure Data Factory for ETL processes, utilized Azure Synapse Analytics for large-scale data warehousing for advanced analytics and machine learning tasks using Azure Databricks.
Building Data Pipelines for Transformation and Loading Data from Azure Blob Storage with Databricks and Python
Job scheduling ETL notebooks with Databricks
Dashboard Design and creating Reports visualizing the KPI developments.
Data Transformation & Validation with Python, DAX and Power BI
Fuzzy String matching
Creating and validating Data Models in Power BI
Requirement engineering at the client
Data Transformation with pyspark
Writing PowerShell Scripts
Dashboard design and reporting for procurement in supply chain transparency
Identifying and analyzing existing and new KPI?s for suplly chain tranparency
Data Transformation with Python, DAX and Power BI
ETL Pipeline Development with Databricks and Python
Writing PowerShell scripts
Streamlined the telematics monitoring solution for primary insurance clients: revamped the existing SQL code base of telematics.
monitoring logic and schema to streamline both the back end and the front end of the primary insurance client-facing Power BI
telematics monitoring solution to holistically track portfolio data.
Completely revamped the data model of the existing telematics monitoring solution from unstructured schema to star schema.
reduced the number of tables in the data model from 50 to 5 and introduced a dynamic sorting algorithm in Python to the existing fact tables to automate sort orders.
migrated code written in DAX to Databricks, SQL and Python
Leveraged existing ETL Pipelines in Databricks SQL to pull and transform batch data in the staging area and load it in blob storage / data lake.
Use Azure Data Factory for orchestration and scheduling of data ingestion jobs.
Revamped the Power BI front-end used by the primary insurance clients across the globe to monitor their telematics portfolio and by the GCU to showcase the unit?s capabilities to the potential primary insurance customers, 1 new primary insurer was onboarded at launch of the new dashboard.
Integrated data anonymization notebook and the schema and logic for personally identifiable information (PII) into the main Power BI pipeline.
Using Cloud-Computed Machine Learning to evaluate the water quality of inland water qualities.
Deep Learning on Google CoLab
Image processing on satellite images
Performed atmospheric correction on the images with the Py6S algorithm (served as Docker image)
Extracted pixel values from the processed images to produce the dataset for predictive learning.
Performed requirement and feature engineering for the data set.
Established baseline machine learning models (RF, MLR, SVR, etc.)
Trained Artificial Neural Networks (ANNs) on Google Colab to benchmark against the performance of the statistical learning algorithms mentioned above
Data Analysis & Machine Learning (ML) development in urban planning:
Data acquisition by web scraping, clustering and unsupervised learning decision tree, exploratory data analysis (EDA)
Unsupervised learning with k-means
Build 4 Machine Learning (ML) classifiers for aerospace:
decision tree (best model, 87% accuracy), logistic regression, support vector machine (SVM), K-nearest neighbor in Python with Sklearn
EDA through SQL and Pandas
Visual reporting in 2 dashboards
Data Analysis and Process Optimization
Requirements and technical analysis
Sample Regression Analysis: regression reports using Python to advise the management in buying different booking system options, and subsequently reduced the booking system expense by 72%
Developed ad-hoc data solutions and combined it with automized mailing.
Generated instructional material and conducted workshops for the department lecturers.
Jupyter Notebook to communicate insights to the stakeholders for the different booking options available.
Development of Sales and Controlling Dashboards over multiple sales and marketing channels in Power BI
Modelling data schema for efficient data storage
Building Data Pipelines and connectors to REST-APIs with Databricks and Python for data provisioning from different sources
Azure Data Factory for orchestration and scheduling of data ingestion jobs
Implementing Business Logic and visualizing various KPIs in Power BI Dashboards for eCommerce (Procurement costs, delivery costs, retour costs, shop fees etc.)
Data Transformation and cleaning
Leveraged Azure Data Factory for ETL processes, utilized Azure Synapse Analytics for large-scale data warehousing for advanced analytics and machine learning tasks using Azure Databricks.
Building Data Pipelines for Transformation and Loading Data from Azure Blob Storage with Databricks and Python
Job scheduling ETL notebooks with Databricks
Dashboard Design and creating Reports visualizing the KPI developments.
Data Transformation & Validation with Python, DAX and Power BI
Fuzzy String matching
Creating and validating Data Models in Power BI
Requirement engineering at the client
Data Transformation with pyspark
Writing PowerShell Scripts
Dashboard design and reporting for procurement in supply chain transparency
Identifying and analyzing existing and new KPI?s for suplly chain tranparency
Data Transformation with Python, DAX and Power BI
ETL Pipeline Development with Databricks and Python
Writing PowerShell scripts
Streamlined the telematics monitoring solution for primary insurance clients: revamped the existing SQL code base of telematics.
monitoring logic and schema to streamline both the back end and the front end of the primary insurance client-facing Power BI
telematics monitoring solution to holistically track portfolio data.
Completely revamped the data model of the existing telematics monitoring solution from unstructured schema to star schema.
reduced the number of tables in the data model from 50 to 5 and introduced a dynamic sorting algorithm in Python to the existing fact tables to automate sort orders.
migrated code written in DAX to Databricks, SQL and Python
Leveraged existing ETL Pipelines in Databricks SQL to pull and transform batch data in the staging area and load it in blob storage / data lake.
Use Azure Data Factory for orchestration and scheduling of data ingestion jobs.
Revamped the Power BI front-end used by the primary insurance clients across the globe to monitor their telematics portfolio and by the GCU to showcase the unit?s capabilities to the potential primary insurance customers, 1 new primary insurer was onboarded at launch of the new dashboard.
Integrated data anonymization notebook and the schema and logic for personally identifiable information (PII) into the main Power BI pipeline.
Using Cloud-Computed Machine Learning to evaluate the water quality of inland water qualities.
Deep Learning on Google CoLab
Image processing on satellite images
Performed atmospheric correction on the images with the Py6S algorithm (served as Docker image)
Extracted pixel values from the processed images to produce the dataset for predictive learning.
Performed requirement and feature engineering for the data set.
Established baseline machine learning models (RF, MLR, SVR, etc.)
Trained Artificial Neural Networks (ANNs) on Google Colab to benchmark against the performance of the statistical learning algorithms mentioned above
Data Analysis & Machine Learning (ML) development in urban planning:
Data acquisition by web scraping, clustering and unsupervised learning decision tree, exploratory data analysis (EDA)
Unsupervised learning with k-means
Build 4 Machine Learning (ML) classifiers for aerospace:
decision tree (best model, 87% accuracy), logistic regression, support vector machine (SVM), K-nearest neighbor in Python with Sklearn
EDA through SQL and Pandas
Visual reporting in 2 dashboards
Data Analysis and Process Optimization
Requirements and technical analysis
Sample Regression Analysis: regression reports using Python to advise the management in buying different booking system options, and subsequently reduced the booking system expense by 72%
Developed ad-hoc data solutions and combined it with automized mailing.
Generated instructional material and conducted workshops for the department lecturers.
Jupyter Notebook to communicate insights to the stakeholders for the different booking options available.