Retail Shelf Product Assortment & Optimisation

Location: Sydney CBD, NSW

Duration: 3 months

Skills required

  • Computer Science, Machine Learning (e.g. collaborative filtering)
  • Research, design, implement and evaluate novel algorithms for predicting product recommendations
  • Experience designing analytic or algorithmic solutions to problems
  • Proven track record of innovation in creating novel algorithms
  • Excellent written and verbal communication skills
  • Ability to clean, transform, and merge data in a procedural language like Python or similar scripting language
  • Experience working with large datasets and Deep Learning algorithms, but not essential

Project Background

Hivery is a “Data” driven company born out of a hackathon in 2015 by talented entrepreneurs (ex CSIRO and Coca-Cola) and their mantra is “data has a better idea”. The Hivery platform is an AI system built on leading edge technologies from machine learning, and their data-driven platform is planning optimal retail strategies around occasion, brand, package, price and channel. It is optimising the scheduling of promotions, and eliciting meaningful customer segments on the back of e-commerce platforms.

Hivery is making waves in Artificial Intelligence and reinventing the way retail businesses use data, through Retain Genome™, they co-design and experiment with their clients to deliver new value. HIVERY specializes in machine learning and mathematical optimization.  Leveraging applied mathematics, the aim is to create a system that will simultaneously optimize space, assortment, and labour leading to the automated generation of high quality, data-driven planograms.

Their client one of the world’s largest retailers, who use out-dated systems and manual processes to review individual retail planograms to ensure right products are allocated in the right stores with the right space allocation while embracing the right business rules and constraints (i.e. attractiveness of the planogram).  This is a very tedious process and is subject to many human biases.

Hivery need a PhD intern to help drive and lead “Assortment Optimisation” efforts Working with HIVERY ‘s optimisation team collaboratively. The intern will have access to real commercial big data; join a team with experimental mindsets with commercial and human centred design focus. This will include experience in both technical and business entrepreneurship as well as travel to USA on business.

Hivery (INT – 0326)

Research to be conducted

  1. Researching latest academic literature / thinking on product recommenders (collaborative filtering)
  2. Research, design and implement a recommender system to align with optimisation recommendations
  3. Conduct mathematical model simulation and test prediction accuracy (i.e. set up training dataset and validation dataset)

Expected outcomes

The aim is to develop a space AND assortment-planning tool that allows the client to:

  1. Increase revenue and decrease cost by simultaneously conducting space and product assortment optimisation.
  2. Save time by being able to automatically generate 3,000+ optimized planograms in a day that require little to no modifications.
  3. The project will be successful if a recommender system/model created provides recommendations with ~90%+ accuracy in predication/ranking.

Additional details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 50% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

To participate in the AMSI Intern program, all applicants must satisfy the following criteria:

  • Be a PhD student currently enrolled at an AMSI member institution.
  • PhD candidature must be confirmed.
  • Applicants must have the written approval of their Principal Supervisor to undertake the internship. This approval must be submitted at the time of application.
  • Internships are also subject to any requirements stipulated by the student’s and the academic mentor’s university.
Applications Close

19 July 2017

Reference:
INT – 0326