Assessment 1 Information

Your Task

Follow the steps within the Google Colab notebook to complete the Python code and interpret the results. At the end of the assessment upload the notebook with your answers and code changes to the portal. Uploading the wrong file will be treated as poor project management practice and penalised accordingly.

Background

Imagine that you are a Business Analyst in a top consulting firm and that you have been tasked with the identification of factors that cause Australian macroeconomic changes.

This skills-building exercise is a workflow that has been designed to simulate this use case and consolidate your practical knowledge of Python, Google Colab, and machine-learning approaches for causal inference.

The Google Colab notebook for this assessment will be provided on the day of the assessment.

Assessment Instructions

Section #1: Machine Learning 

1A: Installation & Module Imports

Step 1: Install Python libraries and import Python modules.

1) Run all the codes that will install and import the necessary Python libraries and models.

Step 2: Load and import macroeconomic data as a dataframe.

1. Load data: read csv file containing macroeconomic data. Create a suitable variable name for the dataframe.
2. Write the Python code that displays information about the dataframe.

1B: Ordinary Least Squares

Step 1: Basic Dataframe Operations

Perform the necessary steps to transform the dataframe in a format ready for machine learning.

Step 2: Perform Ordinary Least Squares

Perform Ordinary Least Squares (OLS) and answer the following question: what proportion of the outcome variable could be explained by the predictor, or feature, variables?

1C: Gradient Boosting Method

Step 1: XGBoost Machine Learning Algorithm

Create an XGBoost ML model in Python. Create a suitable variable name for the model.

Section #2: Explainable Machine Learning 

2A: SHAP

Step 1: Create a SHAP Waterfall Plot of XGBoost ML

What are the Top 5 features that are correlated with the outcome variable?

Step 2: Create a SHAP Force Plot of XGBoost ML

Write no more than one paragraph summary of the insights shown by the SHAP force plot.

2B: Partial Dependence Plots (PDPs)

Step 1: Create a PDP of one feature against the outcome variable

Select one data feature and create a Python code that will display the PDP chart showing effects of this feature on the outcome.

Step 2: Select a second data feature and create a PDP against the outcome variable Select another, different, data feature and create a Python code that will display the PDP chart showing effects of this feature on the outcome.

Section #3: Predict Causal Factors 

Step 1: Use EconML AI Causal Learner

1. Create a suitable variable name for the causal machine learner.
2. Complete the Python code to create an EconML causal learner.

Step 2: ATE Chart – Visualisation of Causal Factors

1. Write Python code that will display a chart of the Average Treatment Effect (ATE) magnitudes, or values, for all the data features.
2. Which of the data features are macroeconomic causal factors?
3. Given the macroeconomic causal factors, what recommendations would you make to the Australian government?

Important:

1. Complete the notebook within the allocated time of 3 hours during workshop.
2. Create a new “text/markdown” cell in Google Colab to record your answers. There is no need to create a separate report.

3. At the end of your class download and submit the notebook with the code changes to the portal.

   Note: ensure that you upload the correct file.

Important Study Information

Academic Integrity and Conduct Policy

https://www.kbs.edu.au/admissions/forms-and-policies

KBS values academic integrity. All students must understand the meaning and consequences of cheating, plagiarism and other academic offences under the Academic Integrity and Conduct Policy.

Please read the policy to learn the answers to these questions:

• What is academic integrity and misconduct?
• What are the penalties for academic misconduct?
• How can I appeal my grade?

Late submission of assignments (within the Assessment Policy)

https://www.kbs.edu.au/admissions/forms-and-policies

Length Limits for Assessments

Penalties may be applied for assessment submissions that exceed prescribed limits.

Study Assistance

Students may seek study assistance from their local Academic Learning Advisor or refer to the resources on the MyKBS Academic Success Centre page. Further details can be accessed at https://elearning.kbs.edu.au/course/view.php?id=1481

Generative AI Traffic Lights

Please see the level of Generative AI that this assessment has been designed to accept:

Marking Guide

A fail mark will be awarded for this assessment:

• If you do not have their cameras on (applies to online classes only)
  • If the submission is more than 10 minutes late
  • if there is evidence of generative AI, contract cheating and/or other forms of academic misconduct.
  • if a quantitative model is not presented and only qualitative discussions are presented.
  • If you present generic/irrelevant information and/or not addressed assessment requirements.

Note 1: A penalty will be imposed if any part of the assessment is deemed by the assessor where it shows an over- reliance on AI-generated content in your answer. There needs to be a demonstration of original thought.

If you want to challenge the penalty awarded based on Note 1, your assessment will be submitted to Academic Integrity for a second opinion and further investigations.