Summary of "PDS Week 1.1"

Purpose

This lecture is an introductory session for a Practical Data Science course. It presents the course outline, what data science is, what data scientists do, and how data science projects typically proceed. It also briefly covers job-market terminology and shows an example job advertisement.

Main ideas and concepts

Course organization: the lecture is split into three parts — course overview, course structure and assessments, and core content (introduction to data science and data science processes).
Definition and role: data science is using data to solve problems, uncover patterns, and produce insights that help organizations make data-driven decisions. A data scientist’s work spans problem definition, data collection/design, cleaning, modeling, testing, visualization, and communication of results and recommendations.
Importance/value: data science is presented as a high-value role (average salary referenced ~US$117K) and has been called “the job of the 21st century” (Harvard Business Review). Employers therefore expect strong, actionable deliverables for that compensation.
Job-market variability: many related job titles exist (data scientist, data analyst, data miner, etc.). Searching different titles yields widely different counts of job listings, but there are many opportunities across titles.
Real-world expectations (example job ad): employers expect hypothesis testing with large, disparate datasets, designing data collection, building models to explain or predict patterns, and using results to improve product/platform or audience experience.

Course-session structure

Part 1 — Course overview: what the course covers and why it matters.
Part 2 — Course structure and assessments: how the course is assessed and organized.
Part 3 — Introduction to data science: what data science is and the general processes used in projects.

Typical data science project / “day in the life” (practical steps)

Understand the business or organizational problem and define objectives.
Formulate hypotheses (especially when planning experiments or A/B tests).
Find existing data or design data collection/experiments to acquire necessary data.
Gather and import the data into a usable environment.
Inspect and clean the data (validation, handling missing values, correcting errors).
Choose tools and environments for analysis and modeling (e.g., Python, R).
Build models to explain patterns or make predictions (statistical or machine learning models).
Analyze results and create visualizations to surface key insights and trends.
Perform statistical tests and validation to ensure robustness and reliability.
Communicate findings and recommendations clearly to stakeholders, including actionable changes (product/route optimization, feature changes, policy recommendations).
Implement and monitor the impact of recommended changes where relevant.

Job-market search guidance

Search multiple job titles (data scientist, data analyst, data miner, etc.) because similar roles are advertised under different names.
Use regionally relevant job search engines (example used in the lecture: SEEK for Australia/New Zealand).
Read job ads carefully to identify common expectations such as hypothesis testing, model-building, explaining/predicting customer or product behavior, and improving user experience.

Example (ABC job ad) — employer expectations

Test product and customer behavior hypotheses with large, disparate datasets; design data collection; build models to explain/predict patterns; identify product/platform improvements to enhance digital audience experience.

Summarized expectations:

Test hypotheses about product and customer behavior using large, heterogeneous datasets.
Design or obtain the needed data.
Develop models to explain and predict patterns.
Use findings to identify product/platform changes or new data-driven services to improve digital audience experience.

Tools and knowledge areas mentioned

Core areas: statistics, computer programming, databases, machine learning, mathematical modeling.
Example tools: R, Python.
Emphasis on visualization and statistical testing to validate and communicate results.

Speakers and sources referenced

Lecture host / Practical Data Science instructor (single speaker; name not provided).
Harvard Business Review (referenced for “the job of the 21st century”).
SEEK (job search engine used as an example for job counts).
ABC (Australian Broadcasting Corporation) — source of the quoted job advertisement.
Generic illustrative example: “Transport company.”