Improving the workflow of Finnair Operations Control through a mathematical model

In Brief

Customer

Finnair

Challenge Finnair wanted to improve customer experience, internal workflows, and cost-efficiency through data.

Results Mathematical models and software tools that improved customer experience and the workflow of the whole Operations Control Center, and enabled remarkable cost savings.

Benefits The mathematical models can be used as a backbone for new applications, making the entire project cost-efficient.

In today's competitive market, in order for airlines to provide the best quality of service, it's increasingly important to take full advantage of their data assets in operational decision making. Nitor’s data science team provided Finnair with mathematical models and software tools. This significantly improved customer experience and workflows in the Operations Control Center, and resulted in remarkable cost savings.

A delayed flight could cause a ripple effect to various other functions
Airline operations are complex. Keeping flights in the schedule, rerouting passengers who missed their connections, and in general, reacting to unexpected events are just some problems Operations Controllers must deal with. At the same time factors such as weather conditions, travel restrictions, and crew availability need to be taken into consideration.

In managing operations, airlines make numerous decisions every day, the outcomes of which may depend on each other, and which can have ripple effects on many flights.

From MVP to production-ready in five months
The project moved into the "production-ready" stage in about five months, which is when it was introduced to a larger group of users. At this stage, the custom dashboard built in the minimum viable product (MVP) was dropped, and results were delivered in Finnair's internal Business Intelligence environment on AWS cloud.

The transition to a wider user base was surprisingly smooth, although the amount of feedback naturally increased remarkably. Thus, some custom forms were introduced for collecting and storing feedback, which significantly improved the feedback loop.

Mathematical model as a base for tools and optimization processes

The core model enables multiple different use cases and tools
Together Nitor’s and Finnair’s team created a mathematical model of the core business, from where they were able to draw some conclusions and see future benefits as well. While still being iteratively developed, the model was mature enough to yield more accurate insight than previous solutions.

As the initial problem was carefully selected, the core model created opportunities for a suite of other tools and optimization processes to further improve the efficiency of business operations. Thus, together with Finnair, several new MVP’s were planned that would be built on this model.

Well established technologies as a foundation
The technologies used for the project were selected based on maturity, suitability for the problem at hand, as well as customer needs. In particular, widely adopted Open Source Data Science tools were used:

Python with Pandas for data wrangling and numerical computing
R shiny and Streamlit for quick prototyping of the user interfaces

Later, the user-facing parts were migrated to the customer’s BI tool, which was familiar to the staff, and enabled easier integration with user management systems.

Significant cost savings and improved customer satisfaction

Significant cost savings and improved customer satisfaction
The suite of applications developed was adopted to daily operational use smoothly, which was supported by training sessions for the end-users as well as an on-going gathering of feedback.

Sharing information about the tools for the organization and quickly incorporating improvement suggestions to the models enabled the inclusion of key people in the development efforts and fast extraction of value from the tools. This resulted in increased customer satisfaction as well as significant cost savings at Finnair.

Helping the operations control center
In airline operations, having a good overview of the flight situation helps prioritize work. With the tools developed, the Operations Control Center staff were able to read and visualize key data about most important flights, helping guide their decisions.

From MVP to production-ready in five months

Internal workshops supported the launch of the project
Finnair had gathered a high-level list of important business problems in internal workshops. Together with Nitor these were prioritized and potential solutions were considered in more detail.

The most useful starting point was identified: a mathematical model of the passengers' journeys end-to-end, to replace less accurate, higher-level indicators that were used previously. This would allow to paint a clearer picture of upcoming and ongoing flights, leading to easier and more informed decision-making.

MVP makes it easier for stakeholders to engage
After choosing the first problem to tackle, the team set out to build a MVP. In close cooperation, the teams of Nitor and Finnair managed to have the MVP, a Python application, periodically running the model, and an R Shiny visualization running in two months.

After that, the team started gathering feedback from the customer domain experts and stakeholders. From this feedback, it became clear where further development efforts should be concentrated.

Iteration is crucial for holistically improving the application
While iterative development continues after the initial MVP stage, the initial iteration is crucial as it improves the application holistically and makes it more robust for the next phase.

Identify new opportunities with sustainable digital development

We digital engineers are here to meet your challenges. Let's harness the potential of your business together.