The great thing about innovation is coming up with an original idea. The great thing about building a business around an original idea is the head start it gives you in defining a unique selling proposition in the market.
On the flip side, really testing your business model where no existing precedent has been set is extremely challenging. Then you must use the results of this testing to convince investors and regulators that your thinking is sound.
Gaining an edge in the Australian Energy Market
ZEN Energy – who are working to develop innovative solutions for their customers, involving battery storage and renewable energy – were faced with this, equally exciting and equally daunting challenge. They required a tool to stress test their business model in an environment that is effectively new to the Australian energy market.
The focus of ZEN Energy is on introducing innovative and sustainable energy technologies to both the commercial and domestic markets. They work closely with some of largest energy users in Australia to reduce costs, increase reliability, and increase the amount of low-emissions energy used in industry.
Building a tool to stress test their business model in a statistically rigorous and data-driven fashion, where no previous standard existed was a task that the data science team at Ignite relished tackling. It was not as if we could just throw data at some pre-existing library.
As large-scale Solar PV generation and battery storage has only recently become cost effective in Australia it is challenging to identify and source relevant data to represent the numerous events that could influence both the generation and storage of electricity. As Chris Smyth from ZEN Energy put it,
“we’re all learning in this new world”
To add to the challenge the team had to develop robust modelling techniques that could be justified. All this under time pressure to enable ZEN Energy to pitch their innovative business model in a competitive environment.
Achieving an enhanced understanding of risk
Using Zen Energy’s deep expertise in the energy market, and data science expertise, we prepared a series of machine learning predictive models that represented a variety of scenarios that could impact earnings.
We worked quickly and iteratively to understand and wrangle a workable dataset that centralised and homogenised multiple datasets from differing sources such as usage predictions, unit pricing and generation – essentially performing extensive transformations, disregarding invalid or incomplete datasets – to produce samples and compositions that reflected the market. These base datasets were large, totalling hundreds of gigabytes, varied and misaligned. Requiring a principles of sound data engineering as a base for data science.
“Leaders want to know the major variables at play and then want to understand the impact of them conspiring against or working in favour of the business.” – Harj Chand, Ignite Data Solutions
Allowing the various levers of the model to be tweaked to mimic any number of potential outcomes in the market without the need for a data scientist to run it each time. This not only gives the users the ability to enhance their understanding at will, but in turn frees the data science resources to work on finetuning accuracy and exploring further scenarios.
“Understanding the data structures, massaging and developing models that incorporate the range of outcomes experienced, and in turn the creation of a model that presents a spectrum of outcomes was one of the founding objectives of the project.” – Chris Smyth, Zen Energy
An innovative business model with a future
The outcome from this project has been extremely positive, as the analytics behind Earnings at Risk modelling for ZEN Energy has readily contributed to the recently announced strategic investment in ZEN by the GFG Alliance. SIMEC Energy Australia, the new name for the joint venture, will work to improve energy security and reduce the cost of power for GFG Alliance and other businesses in Australia.
You can learn more about the SIMEC Energy Australia and Ignite partnership, here.
Alternatively, reach out to us to discuss how analytics could improve scenario and risk modelling in your innovative business.