Earlier work · Data analysis · 2021

Unsupervised Machine Learning

Classification Data Insights

  • Python
  • scikit-learn
  • Jupyter Notebook

This is an archived data analysis project from 2021. My current work is indata engineering.

Aims Grid

Purpose

To unlock an unsupervised machine learning model for the classification of countries, plants, animals and fruits, using pre-trained word embeddings vector.

Stakeholders

  • Research Institute
  • Data science team
  • Data & Analytics Team

End Result

An automated dashboard providing quick & latest insights in order to support data driven decision making

Success Criteria

  • Dashboard(s) uncovering Covid-19 insights with latest data available
  • UK government able to take better decisions & save 10% more lives

Using Unsupervised Algorithm to Train the Data

Data Model

Below is a screenshot of the data model after cleansed and prepared tables were read into Power BI.

This data model also shows star schema of the dimension data from the customer, calendar, products and transactions connected to the facts table.

Star Schema

Unsupervised Machine Learning

Sales Management Dashboard

The finished sales management dashboard with one page with works as a dashboard and overview, with two other pages focused on combining tables for necessary details and visualizations to show sales over time, per customers and per products.

Work with me

Need data you can actually trust?