ACX3300 - Predictive analytics in accounting

There is a more recent version of this academic item available.

Overview

This unit introduces you to Big Data and predictive analytics using accounting information. It will teach you the hands-on skills to manage large-scale financial databases and build predictive models to support strategic and investment decision making. The unit will introduce you to the basic SQL coding skills and SAS statistics software necessary to process and analyse Big Data. It will cover three applications of predictive analytics using accounting data: (1) forecasting future earnings; (2) predicting accounting fraud; and (3) predicting bankruptcy. The unit will be delivered in computer labs to allow you to code and work on data in real-time.

Offerings

S1-01-CAULFIELD-ON-CAMPUS

S2-01-CLAYTON-ON-CAMPUS

Requisites

Prerequisite

ACX1100

6 CP

Introduction to financial accounting

ACX1200

6 CP

Accounting for managers

ACB1120

6 CP

Financial accounting 1

ACC1100

6 CP

Introduction to financial accounting

ACF1100

6 CP

Introduction to financial accounting

ACB1020

6 CP

Accounting in business

ACC1200

6 CP

Accounting for managers

ACF1200

6 CP

Accounting for managers

AND

Business and economic statistics

Rules

Enrolment Rule

Contacts

Chief Examiner(s)

Professor Wen He

Learning outcomes

On successful completion of this unit, you should be able to:

understand the basic characteristics and applications of Big Data in the setting of business decision making

apply SQL and relevant software to manage and analyse large data sets to obtain insights from accounting Big Data

synthesise relevant information from academic research and industry practices to conceptualise predictive models

employ accounting Big Data to produce predictions for corporate earnings, accounting fraud, and bankruptcy

critically assess and test different models and select the optimal predictive models

develop teamwork skills and present the insights from Big Data to the targeted audience.

Teaching approach

Active learning

Assessment

1 - Within semester assessment

Scheduled and non-scheduled teaching activities

Lectures

Tutorials

Workload requirements

Workload

Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled learning activities and independent study. Independent study may include associated readings and practice, assessment and preparation for scheduled activities. The unit requires on average three hours of scheduled activities per week. Scheduled activities may include a combination of teacher-directed learning, peer directed learning, and online engagement.

Learning resources

Required resources

Technology resources