Season 1 Episode 14: Rachel Hassall, SSE, on Data-Driven Decision Making in the Energy Sector

This week, Rachel Hassall, Head of Data Analytics at SSE Energy Solutions, drops into the Hypercube podcast to share her insights on how SSE is tackling data analytics and what the future holds for the organisation and the energy sector as a whole.

Rachel walks us through the nuts and bolts of how SSE is approaching data analytics, the transition from a centralised to a federated model, and how her team is helping enable the company’s vision of leading in low-carbon, localised energy infrastructure solutions.

We get Rachel’s take on a wide range of topics, from the foundational need for data quality to the future and the need for tools like time series forecasting. Rachel shares her perspective on current environmental issues and the need for sustainability to become as important as cost when looking at optimisation.


In this episode, we covered:

  • Insight into how SSE is approaching data, from the tech stack to future projects.
  • The importance of quality data as a foundation for all data initiatives.
  • How rising interest in energy and sustainability is positively impacting recruitment.
  • The importance of avoiding distractions on your data journey and linking to business strategy.
  • The sustainability challenges of data centres and how they impact the green agenda.

The weekly Hypercube podcast sits down with leaders in the energy and utilities sectors to explore how data analytics can help businesses make smarter decisions and accelerate business growth.


[0:29] Rachel gives an overview of her role as Head of Data Analytics at SSE, her career journey to date and the evolution of data analytics within SSE.

[5:45] Adam asks Rachel to give some insight into the tech stack within SSE and asks about the customers and end-users they serve.

[8:26] Rachel explains some of the challenges of communicating forecasting and model performance and ways to approach presenting technical findings.

[9:38] Rachel walks through how forecasting tools have changed and what this looks like within SSE.

[10:48] Rachel and Adam discuss the increasing interest in forecasting and the energy market more generally, and how this has impacted recruitment.

[12:37] Rachel highlights some of the upcoming exciting projects at SSE, including full microgrid optimisation.

[14:10] When asked about market challenges, Rachel emphasises the need for reliable data quality, data access, and data interoperability.

[15:24] Rachel shares her advice for organisations and individuals who are on their own data analytics journey.

[16:16] Rachel shares thoughts on how the next generation will view attitudes toward data storage.

[17:51] Adam asks Rachel to share her view on the big trends over the next five years.


Hypercube Podcast Transcript

Proposed Title: Rachel Hassall, SSE, on Data-Driven Decision Making in the Energy Sector

Host: Adam Sroka
Guest: Rachel Hassall

Intro: Welcome to the Hypercube podcast, where we explore how companies in the energy and utility sector leverage data analytics to make smarter decisions and accelerate business growth. I’m Adam Sroka, founder of Hypercube, a strategic consultancy that supports asset owner-operators, traders, route-to-market providers, and energy services companies to unlock the power of data.

If you’re interested in hearing real-world examples of how data and AI are advancing the energy sector, this is the show for you. 

Welcome back to the Hypercube podcast. Today I’m honoured to be joined by Rachel Hassall, who’s Head of Data Analytics at SSE. Rachel, great to speak to you today. What does a Head of Data Analytics do at a company the size of SSE? 

Rachel Hassall: Good morning. Good morning. So being the data nerd that I am, I actually record how I spend my time.

So I can say that, yeah, 22 percent of my time is with the team, with my team. 8 percent of my time is doing technical data and analytics type stuff. 20 percent of my time is doing project and product management. And 11 percent is business development, 12 percent is engagement with the business, and the rest is other stuff.

Adam Sroka: That’s it. So, being a consultant, I love recording my time in timesheets, and everyone surely loves timesheets, but that’s really interesting. Okay, let’s rewind a little bit. Be interested just to hear, how did you get there? Like, could you share a bit about your journey from doing like, yeah, demand forecasting for gas at power stations, and then you, what, you made the switch to electricity and like, what was the journey to where you are now?

Rachel Hassall: We want to be a leader in low carbon, localised energy infrastructure solutions, which is an absolute mouthful there that I garbled out. But yeah, I started off in the energy industry, but I started off more on the gas side. So I started working for an energy consultancy firm doing software stuff, software consultancy, but spent six months doing data science and like absolutely caught the bug.

Like it opened my eyes. It was fantastic. Like, I got addicted, started doing more data analytics projects, moved to a gas transmission company to lead and set up their data, data science function, doing things like gas demand forecasting, which is interesting because one of the hardest components to predict for gas demand.

Um, there are gas power stations. And so to be able to predict gas demand for power stations, you have to start understanding the whole electricity mix because gas power stations are used to balance everything on the electricity side. That’s the 

Adam Sroka: models. Yeah. 

Rachel Hassall: So like I was getting into like the Alexa on data and just starting to unpick everything that was happening in the electricity market to then do this, this gas demand forecast, which put me in a really great place to then transition into SSE energy solutions.

Thanks. because I started to understand more about the electricity market. So it was kind of a little bit of a winding path to now setting up the data analytics team within, um, the energy solutions SSE. 

Adam Sroka: So unique thing, I think to the energy sort of sector is the kind of pendulum of engagement with data analytics across a lot of companies.

Like, You either get, in my experience, like everyone wants involved and everyone’s got great ideas for stuff you should be doing or building, or you go completely the other way and it’s all like cyber security nightmare, or you become yet another IT team and like, where on the pendulum do you think you live?

And have you got any kind of good stories around that? 

Rachel Hassall: Yeah, interestingly an SSE like pretty big company with lots of different business units like distribution, transmission, renewables, thermal and my area enterprise. So I came in like two and a half, three years ago and I came in at like a change point on how data analytics was done with an SSE.

Previously um, we had like the, the, it was centralised. So there was a centralised data analytics team covering all those different business areas and that’s like a 10, 000 plus organisation. From what I gather, I mean, I wasn’t there at the time, right? So this is kind of how I understand that it was like the data analytics team would kind of parachute in for use cases, there’d almost be like a, a dragon’s den approach to solving problems.

So business units would have to come to the centralised team. to get their time and solve these problems. And so when I came in, we’re moving to a federated model. So each business unit would have their own data analytics team so that it would sit a little bit closer to the business. And so, yeah, I’ve kind of been interested in that transition from the centralised to the federated.

So it means that every business unit is doing it slightly differently. So some business units are having their data analytics team sitting within IT. Strictly within the business. And so like, yeah, I think it’s different within, there’s like subcultures within the company in my area. Um, so I sit within the business, and work quite closely with it.

Um, but like, so it’s, we’ve got, our area is very much considered like the entrepreneurial part of SSE. We’re quite unique in that we’re building like software products to sell externally. Um, as well as within company data analytics, if that makes sense. So we’re pretty agile and seen as the entrepreneurial part of SSE, despite being quite a large organisation, maybe not as entrepreneurial, maybe not as agile as like a smaller startup, but kind of in the middle of those two worlds, perhaps.

Adam Sroka: What about tech stack? Like, can you share anything about the tech stack, like tools, technologies, like anything for the nerds of us in the audience? 

Rachel Hassall: Yeah, one of the fallouts of moving from the centralised to the federated model is that across SE, the centralised team set up what we call a DNA platform, a data analytics platform that sits on Azure.

So within that, we kind of get to pick and choose what we want. My team, we’re, we use a lot of Databricks. For us, it also has the benefit that for the products that we are looking to sell externally, we’re focused on AWS there at the moment. And so Databricks has that multi cloud stuff, so it gives us a little bit of comfort.

If we want to take what we’ve learned internally, and then commercialise it externally, that transitions a little bit smoother. 

Adam Sroka: Okay, tech stack. So are you doing like, Delta Lake and stuff like that, like forecasting and time travel, all that good stuff? 

Rachel Hassall: Yeah, we’re quite a new business with an SSE, so like, We’re quite fortunate in that we’re just setting up IT systems and kind of doing a lot of the building of our data infrastructure.

So I say we’re pretty early on in that journey. We started using Delta Lake, we’re doing a little bit of time travelling. Probably not that I have experienced it yet, I would say. To be honest, 

Adam Sroka: It’s good. It’s a good safety net to have, but yeah, to make the most of it, it’s quite tricky. I think it’s, yeah.

Rachel Hassall: And like, I think also like, especially with forecasting, right, like the history is really important for building your models because you want to see what the view was at the time that you’re making the forecast for like hindcasting and stuff. And I think there’s benefits to like traditional slowly changing dimensions, type one, type two, type three, being documented within your data structures to make it a little bit more intuitive to see what’s going on at times.


Adam Sroka: Yeah. Okay. So interestingly, it’d be good to understand, like, who are your user personas, like end users? It’s not actually apparent to me who your customer is, like it’s businesses, but in the business, what kind of people? Are they traders? Is it a large organisation? 

Rachel Hassall: Yeah. Okay. So. Our external customers are people at university campuses that are wanting to decarbonize their campus.

So they want to install solar batteries and they want to help in optimising that or trading the energy that these assets are generating. So large businesses, campuses, data centres. are a really big emerging area for us. Companies that have multiple buildings as well. So where we can do things like building energy optimization and things like that on a slightly smaller scale compared to the whole energy system optimization.

So yeah, building energy managers, sustainability managers, that kind of thing. 

Adam Sroka: Yeah. And so, cause I was getting to, when you get into like forecasting and like model performance and stuff like that, even to like technical people, If they’re not, like, absolute data nerds, how do you communicate, like, actually, this model is better than that one, and things like that, like, do you have any good tips and advice for, like, saying, okay, this is how to really, how you present these kind of hard technical findings to mixed technical audiences?

Rachel Hassall: Yeah, I don’t know, like, there’s not much. Maybe some of the simpler error metrics people can get their heads around, like mean absolute error or something like that. If you can put it in pounds and pence, I think that helps. So they understand financial risk, like, you know, graphs with confidence intervals and stuff.

So they kind of get a vibe for how confident we’re feeling, I think. 

Adam Sroka: So what about actual forecasting tools? Have they changed from over the last few years? Are you still using the good old, like, tried and tested statistical time series y stuff, or is it all large language models, and what is it, like, forecast LLM is these days?

Rachel Hassall: I think we’re probably in the middle. Statistical models are still, like, interstate. Like, in terms of an ensemble forecast, there’s still statistical models in there. We’re not quite at the forecast LLM or anything like that yet. Um, but yeah, I mean, neural nets and stuff are still in there, but I mean, there was forecasting done for gas, for example, using neural nets and the Cisco stuff, like from like the eighties, nineties, right?

So I think the thing that we’ve put a lot of focus on is data quality. So we’re like doing a lot of anomaly detection on our historic data and changing how we use that to train our models. That’s probably had the biggest impact on forecasting over the last 

Adam Sroka: year, I would say. That’s good to hear.

That’s like you tell everyone that and no one believes you, but it’s good to hear there’s a case study. I’m going to keep this soundbite forever. Because it’s a hard sell, right? Like, the quality, it’s always like the boring, the boring stuff and the plumbing, but yeah, it does start to elevate like everything downstream and so on and so forth.

Rachel Hassall: I think I was listening to one of your previous podcasts with Sam Young, right? And definitely agree that we’re in need of a revolution on time series forecasting, like it’s coming. 

Adam Sroka: It’s starting to get a bit of a buzz as well. It’s quite fun. And I think there’s been so many false starts and things like the Zwillow profit scandal and that and like taking a back step.

Yeah. I think it’s starting to get a bit more interesting. People are starting to get a bit more interested in energy. Have you found that? Oh, for sure. Yeah. Like techies and data people want in now. 

Rachel Hassall: Yeah. Even people in my personal life. Like, people are like, asking what I do, and that’s never happened before.

Like, people are interested in the nitty gritty, like my mom and dad. They’ve recently installed a solar panel and a battery, and they’re like, how should we optimise this? Like, oh, we exported two pounds 50 to the grid. That was literally yesterday, by the way. And like wanting me to get involved and I’m wanting to learn more about what I do because, you know, what I do is basically a bigger version of what they’re doing in their house.

Right. And like, yeah, it’s been really good for making me more excited at the party. 

Adam Sroka: Finally. Well, actually. 

Rachel Hassall: Yeah, this is my moment guys. 

Adam Sroka: Take it. Take it. 

Rachel Hassall: But also with recruitment, like it’s much easier to recruit people, understand the mission of net zero and can feel quite passionately about it.

It’s yeah, it’s made recruitment a lot easier, I think as well. 

Adam Sroka: I mean, I found that actually selfish, from an evil capitalist perspective, you can get really good talent for a lot less than like they could otherwise get like a big corporate because they actually want to contribute to the mission. And they’ll stay longer, and they’re like As long as you’re over that threshold sort of compensation, they’re really happy and it’s really lovely to see.

It might be generational as well, but. 

Rachel Hassall: I guess as long as you can show the value in what you’re doing, right, that it is contributing to like the mission statement. 

Adam Sroka: Okay. Any exciting projects we can spill the beans on? Anything like that you’re geared up for this year? 

Rachel Hassall: Yeah, definitely. We’re building up to full kind of microgrid optimization. You know, we’ve built a really good foundation with our demand forecasting. We’re working on building energy optimization at the moment, which is like a sub component of the kind of whole systems optimization that might be good stuff. So we’re kind of ramping up to deeper and deeper optimization. So really excited and working with some really good partners and the team to, uh, you know, solve some really meaty problems.

I think it’s cool because the problems that we’re solving are pretty close to cutting edge research and the gap between these two I think is getting smaller, which yeah, fear but also excitement, right? 

Adam Sroka: Yeah, I think we’re starting to see, like, the tail end downwards. rules based optimization setups, like seeing the diminishing returns.

And because it just takes such a lot of big brain maths to do optimization well, that everyone’s just like, Oh, I don’t understand it. I don’t want to do it. But so many competitors now in the market that actually it’s just becoming a necessity. You’re in a unique position, right? People are coming to you with buildings or, or estates and saying, Oh, hell, very few people are sat where you’re sat that can see the weird, the wonderful, the super common, like all that.

Do you think anything to watch out for and look for that’s going to be a challenge for people? 

Rachel Hassall: There’s the reliable data quality, data access, data interoperability, also a mouthful to say that you can roll out for any data problem. I think I’ll be really interested to see how off jam and the data and the networks work together to improve data access and data interoperability.

So that makes it easier to kind of UK wide. Engine system optimization products and things to develop. Yeah, I think that’ll be the area, the area to keep an eye on and hopefully progress there is really fast. 

Adam Sroka: That’s the kind of thing that just helps everyone to do more faster, less pain, less chaos. 

Rachel Hassall: I think there’s good progress being made with a number of networks looking at opening up their smart metre data, SSE being one.

The more data, the easier it gets, I guess, to a certain degree. 

Adam Sroka: So what about people like organisations, but, and. Or individuals that are early on their journey with data analytics and things like that, like from your experience, what kind of advice would you give from people that are starting to?

Look at this seriously and maybe get up that maturity curve to kind of a bigger team and do more. 

Rachel Hassall: Yeah. I think one of my lessons learned, right, was like focusing and not getting distracted, starting small maybe and linking it to your business strategy. So if you can get that golden thread of what you’re doing right through to your business strategy, that’s going to be a really compelling story to tell.

So that does mean maybe not getting distracted by. large language models, and some other things. until you’ve got that kind of golden thread. I mean, it’s the same with everything, right? Start small and build from there. Yeah. A real focus on building a team that is happy to change and develop in that way.

Cause like change is inevitable. Yeah. If you can build a team that are really comfortable with that, it’s going to 

Adam Sroka: make your life a lot easier. All right. What about really juicy stuff? If you’ve got any hot takes on tech or the energy system, anything controversial? 

Rachel Hassall: This is a bit tangential and more winded, but You know how with each generation you kind of look back at the generation before and you’ll be like Oh, they didn’t realise this, and that’s really wrong now.

So for example, aerosols and we’re hurting the ozone layer and stuff like that, right? I do wonder, like, if the thing that is like that for us now, the next generation will be like, Hey guys, what were you thinking? Is around the use of large language models, the sustainability of cloud compute. and data storage.

So the fact that you’ll take like 10 photos of the same thing and store them, like, I think that might be maybe the thing the next generation is gonna be like, Oh guys, what are you doing? 

Adam Sroka: Yeah. Like let’s put a new data centre to store the 40, 000 photos that me and everyone I’ve ever met has taken. Over the last five years and 

Rachel Hassall: yeah, 

Adam Sroka: I think the sustainability point is really important.

There’s a whole thing about how some of these data centres could actually cause a water crisis in America in part of where they are and things like that. You just think like, was this what we were supposed to be doing? Like, 

Rachel Hassall: I mean, the good thing about the data centres is that I think they’ve really pushed forward the green agenda, like Microsoft or, you know, I’ve been really looking towards 24 seven carbon free energy, big investors and pushing that forward.

So like, it does seem that it’s pretty high on their agenda at least, like, and it keeps companies like mine, like it gives us a focus on where we can help decarbonize and there’s like pretty cool, innovative new ways of doing it right with like heat networks and, and stuff on, on the data centres. 

Adam Sroka: It’s a cool place to play at the moment, I think there’s lots of interesting stuff.

Alright, last one from me before we wrap, what do you think? Big trends over the next five years, either in data or tech or the energy sector, they’re like, what do you think is going to be big in 2029? 

Rachel Hassall: I’m hoping that like what we’re talking about, I’m hoping that the sustainability piece of what we’re doing becomes more transparent.

So you know, we focus on costs when we’re optimising our models and our infrastructure and stuff. But I’m hoping that sustainability will be an equal measure in that, and we’ll become more transparent from a lot of the big tech companies as well. I think that would be what I hope for, and it might be then we can get into cool things like optimising the timing of our model, depending on what generation or what the generation demand mix is, is like.

So like that other layer of optimization and stuff like that. I think, yeah, that would be the big thing I hope for, I guess. Very true. 

Adam Sroka: Well, last one that I always ask, uh, is there anything you’d like to promote or like, if people want to find out more about you or the work you’re up to, where, where can we send them?

Rachel Hassall: We’ve got a great website, , which we’ll be launching into the brand Trutonor soon, which covers off a lot of the stuff that we’re doing around data optimization flex. So that’s really the place and we’ll be publishing lots of case studies and cool stuff. So yeah. 

Adam Sroka: Very cool. Well, look, it’s been a pleasure to speak to you.

Thank you very much and wish you all the best at SSE. 

Rachel Hassall: Thanks, Adam. 

Outro: And that’s it for this episode of the Hypercube podcast. Thanks for tuning in today.

If you have any questions about the topics we covered, you can reach out to us on LinkedIn or check out our website at You can also join Beyond Energy, our Slack community of data leaders from the sector. There’s a link to sign up in the episode description. We’re just getting this show off the ground, so if you like today’s episode, please leave us a rating, review, or subscribe wherever you get your podcasts.

It all really helps. See you next time.