Applying machine learning to business outcomes at Travelopia

Travelopia has changed its focus from a technology approach to business outcomes and has adapted Agile and Lean to deliver machine learning solutions. This has enabled them to deliver business models powered by machine learning faster and better.

Sreekandh Balakrishnan, ‘Director – Innovation’ for Travelopia, and Simon Case, Head of Data for Equal Experts, spoke about machine learning to Travelopedia at Lean Agile Scotland 2022.

The first iteration of machine learning was very technology-centric, Balakrishnan said:

We took a technology stack approach and built a data lake before understanding business use cases. We took a big bang approach to delivery, one big team, with a promise to deliver more use cases once the data lake was in place. At the end of 18 months we had 3 models in production but no fewer business units using it.

Suggested case to figure out which business improvement you want first:

Start small, pick a slice of value, and learn not only about the technology, but also about how to frame the problem, how to engage users, how to deliver results to downstream users or services, and what other organizational challenges (people, process before and finally technology) there are.

Balakrishnan said they weren’t getting the technical or commercial impact they wanted. They made some changes to become leaner and shifted their focus to business results:

We had a second iteration using the new lean and agile approach and were able to deliver 2 templates in 3 months that are being used and creating business value. After this success, we adopted this as our methodology. We have since gone on to 10 models in production for 5 brands. All are being used in the business and some brands are generating a 21% increase in business. In fact, I can now deliver a new model to the company in less than 10 weeks.

InfoQ interviewed Sreekandh Balakrishnan and Simon Case about machine learning on Travelopedia.

InfoQ: What did you learn from how you initially applied machine learning and how did it impact your approach?

Sreekandh Balakrishnan: We applied lean and agile principles: discover what’s valuable, deliver in small increments, and keep learning (and pivoting until you get it right).


We have shifted the focus from a technology to the business result. We took the time to figure out what the company wanted and how they wanted it delivered. The team was too big, so we reduced it from 40 people to a team of 6. We found that a lean, cross-functional team was able to make progress faster and keep the focus on what the business wanted.


We stopped building a data lake that satisfied all ML needs and started focusing only on preparing the data we needed. This also had the side effect of reducing our cloud cost to 10% of what it had been.


We also consciously moved away from GUI-driven tools. We had used them in the first iteration, but found it difficult to apply modern software development techniques (TDD, pair programming) when using them. Instead of speeding up our delivery, they were slowing it down.


Eventually, I recognized that I needed the consent of the company, which was more used to big bang delivery. So I made sure I had an executive sponsor who understood and believed in this approach. This has really helped our relationship with the company and made it easier to adopt ML models.

InfoQ: In your talk, you suggested not to worry about data platforms, but rather how your teams will self-organize. Can you explain why?

Simone Caso: Machine learning is a team sport. You need data scientist and data engineers to work together. They are different disciplines: data scientists are experts in algorithms and mathematics, but often lack the software skills necessary to build reliable products. It can be tempting to keep them separate, but if you do, they won’t learn the techniques needed to put their work into production.

Balakrishnan: Things started to change for us when we streamlined the team and created one small cross-functional team. With data engineers, data scientists, and business analysts working as one team, they understood users better and were able to make quick decisions and compromises on the technology stack and ML model.

InfoQ: What is your advice for companies considering using machine learning?

Balakrishnan: Start small and don’t worry about buzzwords! Keep business stakeholders close to you and invite them to attend daily standup/planning meetings. Create the first win and go into production. Remember, it’s a learning curve for you, your team, and your business.

Case: Build your expertise iteratively – start with a steel wire – the first vertical slice that provides useful business value. Use it to learn quickly, and when you’re satisfied, it serves as a template that you can use for other ML models. If you’re lucky, become a paved road – a way of working that allows you to quickly introduce new models into the business.

Leave a Reply

Your email address will not be published. Required fields are marked *