Moxy Consulting

Better algorithms to drive market
place businesses

Whether you need to match readers to articles, consumers to products or breakdown calls to mechanics, we develop smart algorithms to lift the performance of your business.

Many of our clients have a marketplace dynamic at their core. That is, they have consumers on one side of their business (demand), and a mix of inventory, articles or businesses on the other (supply). 

Typically, supply and demand are matched through a website or business application and those interactions are powered by an algorithm that chooses what to show. Depending on the industry, that algorithm has different names: from recommendation engine, sort algorithm, dispatch algorithm or matchmaking approach.

Uneven arrival rates increase the difficulty of matching supply to demand.

At Moxy, we are experts in improving the performance of the algorithms that sit at the centre of the marketplace.

Our Clients

Case Studies

Australian Doctor Group

Australian Doctor Group is the publisher of Australian Doctor – Australia’s leading source of medical news for General Practitioners.

Service Organisations

Service Organisations face particular challenges in the delivery to customers of consistent and reliable service.


OurDeal is a group buying website that was purchased by industry leader Groupon. Customers come to the site in search of deals on products,


Connecting high-quality Australian businesses with customers who need them. With over 300 categories, from plumbers and electricians to pet groomers,

How We Do It

With more than 15 years of experience in developing algorithms, we have a tried and tested methodology for improving performance.

1. Orientation

We start by meeting the team, gaining access to the data and getting a feel for the current approach to the problem.

2. Framing the problem

We workshop ideas to bring alignment between the different stakeholders who have an interest in the algorithm, so that we all leave with the same definition of what a success algorithm looks like and we have clarity on what we are optimizing for.

3. Design the Features

We analyse which existing features are important for understanding the supply, demand and matchmaking problems. We ask the question, what data do we wish we had? What data would transform our understanding of the customer?

4. Truly Understand What Drives the Customer To Choose a Particular Product

The essence of our solution is the ability to predict what a given customer will do when presented with a particular product.

5. Simulate different recommendation algorithms

Now that we can reliably predict the behaviour of our typical customers we can experiment with different matchmaking algorithms

6. Build out the solution

The model needs to be moved from the benchtop to production. It is here we address the concerns around:

7. Deployment and Monitoring

We need to monitor the impact of the interventions to make sure that the business is following the new process and that people are acting on the predictions We need to monitor the performance and reliability of the deployment. Is engineering stable? Is the recommender playing nicely with the other systems?

Our Team

David Neale -

David is an expert in the ancient art of merchandising and applying those principles to digital businesses. He is an Industrial Designer by training and came to love data as the best way to make sense of how users interact with digital businesses.

Wei Yiju
Data Scientist

Wei is an experienced data scientist with experience developing models and data pipelines in high demand, high availability environments.

Technologies We Use

At Moxy, we find that most of our projects use some combination of the following tools.

Contact Us

Complete the form, or email us on enquiries at Alternatively, reach out to us via LinkedIn.