Cutting through the noise with individual travel recommendations
Scandinavian Airlines can become even more personalized in their communication to potential travelers, targeting the customers at the right time and with the right content. By using a model build in SAS® Viya®, a Hackathon team from Forefront was able to pinpoint the likelihood that a person is looking to book travel within the next week.
When planning a trip, travelers usually go online to find inspiration and ideas of where and when to travel. Once there, they are bombarded with information from different companies trying to sell them travel packages. The barrage of information can be quite overwhelming and is often irrelevant or impersonal.
Airlines and travel companies have insights on where people like to travel and when. However, this data is not being used optimally. Travel industry professionals have the potential to use customer history and research to create bespoke communications for new and existing customers.
As part of the SAS® Viya® Hackathon, an analyst team from Forefront, including two master thesis students from Industrial Engineering and Management at Umeå University, joined forces with Scandinavian Airlines to demonstrate how existing data on people’s travel preferences can be utilized to promote the best travel experiences.
Essentially, we want to be able to answer the question: When does a customer have their travel mood on, and to which destination will the customer travel? Stefan Stark Hackathon Team Lead Forefront
Using data to predict where and when customers will travel next
For the project, demographic data, customer loyalty, online search patterns, and booking history were loaded into the SAS® Viya® environment. Data was then visualized, cleaned and put into models to find out if customers are in a booking mood. This data was used to predict the customers’ probability of booking a flight within the next 7 days.
Within SAS® Viya®, four models (logistic regression, decision tree, random forest and a neural network) were compared and tested to find the best solution. The comparison, coding and testing of the models were performed by the students under supervision by Forefront.
While each traveler has a different background there were some common threads. Age, gender, geographical location, style of living, and more. These variables were put together to create a so-called look-a-like persona. How do people like you like to travel?
It was important to find a solution focused on personalization and a data driven customer journey. This way, Scandinavian Airlines can be even more relevant for their customers in all channels, email, webpage and different campaigns and marketing activities delivering even more value for both customers and Scandinavian Airlines Stefan Stark Hackathon Team Lead Forefront
We hope that with this solution, travelers will have a better experience when choosing their next destination. Planning a trip should be fun and with this solution it will be personalized to fit your travel needs Nathalie Jakobsson Hackathon Technical Lead Forefront
Challenge
- Travelers often receive an overwhelming amount of lot of untargeted communication from travel companies.
Solution
- Demographic data, customer loyalty data, online search patterns and booking history were uploaded into the SAS® Viya® environment.
- A timeline and booking window were defined, new variables was created based on search history, allowing the data team to determine whether a person is ready to book their travel.
Benefit
- Using an even more personalized and data driven customer journey, Scandinavian Airlines can be even more relevant for their customers in all channels.
About Hack In SAS Viya
In association with Intel and SAS Nordic User Group “Fans”. SAS hosted the competition “Smarter Together” for SAS partners. Here, teams of analysts and data scientists demonstrate the value of open data combined with SAS® Viya® in the cloud and open source technologies.
SAS provided the SAS® Viya® platform with a number of SAS tools in the cloud for easy access through saasnow.com. The nine participating teams built showcase based on a number of SAS software products including: Visual Analytics, Visual Statistics, Visual Data Mining & Machine learning, econometrics, and optimization.