In the Australian energy utilities sector, you've likely heard that some of your competitors are investing in the science of data - putting great stake in the internet of things (IoT) and business intelligence tools to gain detailed customer insights and get a leg up on the competition. Many see big data analytics as the future of the industry, but what does it mean for utilities in Australia, and how can they use it?
What could data analytics mean for Australian utilities?
Companies around the world are gathering a host of information - sensor and network data, customer attitudes and demographics, billing histories, energy demand forecasts, and more - in an effort to create a more personalised, flexible service.
Customer satisfaction is the next major battleground for Australian utilities.
Customer satisfaction, according to EY, is the next major battleground for Australian utilities. The company's Digital Australia report suggests that Australia is lagging behind the rest of the world when it comes to innovation and customer happiness.
But yet, the solutions are already close at hand. EY goes on to recommend that local utilities adopt analytics in order to provide a "deeper, more intuitive service."
The Machine Learning Primer: A SAS Best Practices e-book
Download the Utility analytics in 2017 whitepaper, which explores the issues and trends that are shaping how utilities are deploying data and analytics to achieve their business goals.
Free utility analytics whitepaper
4. Apply appropriate scientific rigor
While extremely powerful, machine learning isn’t a magical, self-correcting analytical panacea. In practice, developing a machine learning application is an experimental and iterative process. This is true even when using well-known algorithms. In every case, the algorithm must be trained on and tuned for the business context and data at hand.
Whether you’re a machine learning beginner or an experienced practitioner, a healthy dose of skepticism and solid statistical reasoning, scientific and data analysis is critical.
5. Make it just complicated enough
Generally speaking, more data wins. But do more features (aka attributes or data points) also equate to better outcomes? Not always. The catch is that larger data sets beget larger variations in data and a larger potential for predictive error.
In many cases, weaker models with more data do better than more complicated models with less – even if the data is dirtier. This is the basis of ensemble modeling techniques that use the “power of the collective” to predict results.
Deploying machine learning artfully is a balancing act. One in which the incremental predictive value of complexity must be weighed against interpretability, ease of use and applicability.
6. Actively engage business users in validation
Data scientists must apply due diligence as the model is created and tuned. To do so, they must effectively communicate and collaborate with data and business domain experts to validate and vet the model.
This is critical to ensure the team has, among other things:
- Validated that all the options have been considered.
- Accounted for potential bias.
- Identified the impact and implications of putting found insight into action.
Whether you’re a machine learning beginner or an experienced practitioner, a healthy dose of skepticism and solid statistical reasoning, scientific and data analysis is critical. Kimberly Nevala Director of Business Strategies SAS Best Practices
Consider analytics in the context of weather disasters
The modern world is not as simple for energy utilities as it used to be. The simple addition of renewable energy like wind and solar means the grid is less stable, and more prone to sporadic events. But this is one instance where the internet of things can be linked with powerful analytics tools to keep companies one step ahead of chance.
For example, imagine collecting all of the data from your company's PMU sensors and storing them using a cost-effective Hadoop framework - even though we're talking about a near-uncountable amount of data, it can be easily stored, accessed and, more importantly, analysed.
One day, a weather event strikes a large population of your customers and the grid goes down, or is damaged in some capacity. With the right data, you can quickly diagnose the error - was it equipment failure, a lightning strike, or something new? - and assess the impact at, fittingly, lightning speed. Your technicians can go out to repair the damage, while your customer service agents answer the phones armed with the right knowledge to assure customers that their power will return soon.
With the power of storing and analysing data, you've created a better customer experience. And this data can be further analysed to predict these events in the future, making you more efficient at dealing with them every time.
Examples of how utilities are using big data analytics
Let's examine two case studies of utilities companies in Australia and around the world utilising big data analytics to improve their service.
Forecasting future energy demand in an increasingly renewable
energy world isn't exactly easy.
About the Author
Kimberly Nevala is a director on the SAS Best Practices team where she is responsible for industry education, key client strategies, and market analysis in the areas of business intelligence and analytics, data governance, and master data management. Kimberly has more than 15 years experience advising clients worldwide on sustainable business strategies, business-IT alignment and enterprise solution deployment. Her work has been featured by CIO Asia, Knowledge World, Network World and Datanami.
At home in Australia
Take Origin Energy, for example. When the Origin team started talking to us here at SAS, they wanted to better understand their customers' demands. But of course, as we know, forecasting future energy demand in an increasingly renewable energy world (and a country with unstable weather like Australia) isn't exactly easy.
Well, this is where we deployed SAS Energy Forecasting. By using Origin's collected data and SAS's powerful tool, the company could move away from the traditional monthly bill of random pricing to a Predictable Plan of charging customers the same amount each time. Now customers can budget confidently, and are never shocked by an unexpectedly high energy bill. This has been highly successful in increasing Origin's customer loyalty.
An overseas example
What if your company experiences large amounts of churn? Collecting data and analysing it closely can help here too, just like it has helped EDF Energy in the UK.
EDF collects three data sets to try and classify customers and identify who is most likely to leave. By comparing attitudes with lifestyles and demographics, EDF - through the power of SAS analytics - can help its marketing team prioritise customer communications based on identified risk. For example, EDF salespeople can focus on upselling customers who are actually likely to buy, instead of rocking the boat with those who are not.
Now although these two examples only scratch the surface of how big data analytics can help utilities companies in Australia, you begin to see that nearly any customer or service problem can be solved with the right information at your fingertips. If you'd like to learn more about how SAS can help your company, get in touch with our team today.
- Article The Humanity in Artificial IntelligenceCould artificial intelligence be the change agent we need to solve many problems around the globe? Read how AI could accelerate our ability to have a a positive, lasting impact.
- Article How AI and advanced analytics are impacting the financial services industryTop SAS experts weigh in on the topics that are keeping institutions up at night and fraudsters in a job.
- Article IFRS 17: Waiting is not an optionIFRS 17 is a principles-based accounting standard for the future-oriented valuation of insurance contracts. Designed to increase financial transparency, IFRS 17 requires insurers to report in more detail on how insurance and reinsurance contracts affect their finances and risk.
- Article Building confidence in your customer experienceForbes Insights surveyed more than 350 leaders at large organizations to determine how they are using data and analytics to power the customer experience.