1.1 Defning Data Science

Assignment: Data Science Scenarios

Introduction

This is a post about my assignment submission from Microsoft’s Data Science for Beginners repository. Specifically, this is submission for the first lesson.

Problems

1. How can you use data to improve education process for children in schools?
2. How can you use data to control vaccination during the pandemic?
3. How can you use data to make sure you are being productive at work?

Answer

Prior to giving my answer, I would like to justify that filling the assignment using table format while I write it on raw markdown may render my work excessively time consuming. Therefore, I’m writing it in list format.

Education

Student’s comprehension level

• Data collection: pre-test, post-test, exercises, mid-term exam, final-term exam
• Data storage: Microsoft Excel, Google Spreadsheet, DBMS, CSV
• Insights: Teaching approach, teaching strategy, teaching methodology, curriculum development, test design, option distractors, item difficulty index (for multiple choice)

Teacher Likability

• Data collection: Student’s presence list (daily), Teacher presence list
• Data storage: Microsoft Excel, Google Spreadsheet, DBMS, CSV
• Insights: Student’s most anticipated teacher, teacher professional development

Test Quality

• Data collection: mid-term exam, final-term exam
• Data storage: Microsoft Excel, Google Spreadsheet, DBMS, CSV
• Insights: Test quality, curriculum development, item analysis (distractor, discriminiation index, difficulty index)

Vaccination

Vaccination Survey

• Data collection: Identification number, vaccination date
• Data storage: Paper-based logs, Microsoft Excel, Google Spreadsheet, DBMS, CSV
• Insights: Monitoring which state/region have lower number of vaccinated person

Vaccine Effectivity

• Data collection: Patient ID, Patient basic information, vaccination status, vaccination date, symptoms, status (deceased/alive)
• Data storage: Strict DBMS
• Insights: Confidence level of the vaccine curing the virus.

Vaccine Side Effects

• Data collection: Patient ID, Patient basic information, vaccination status, vaccination date, symptoms, status (deceased/alive)
• Data storage: Strict DBMS
• Insights: Vaccine improvements, vaccine dosage, vaccine terms of use(?)

Productivity

Employee Performance

• Data collection: Employee ID, Employee Department, Employee Job Role, KPI, Target Achieved (boolean)
• Data storage: Strict company DBMS
• Insights: HR decision to train employee

Employee Churn Rate

• Data collection: Employee ID, Employee Department, Employee Job Role, KPI, Target Achieved (boolean), Employee Presence List
• Data storage: Strict company DBMS
• Insights: HR decision to make new reward system