Predictive analytics is often associated with e-commerce heavyweights like Amazon and Google.
However, few know what the term actually means, and how it can be used to enhance business processes and practices.
The premise of predictive analytics is simple: intelligent software analyses what’s happening now, and uses this data to model what the future will look like.
Recent developments in artificial intelligence have taken this concept one step further, with newer systems being able to predict the more complex characteristics which influence business progress – such as human behaviour.
Predictive analytics is easier when looking at people and known processes – harder when predicting things like economics.
The good news is there are plenty of areas in travel management in the sweet spot, allowing travel managers to influence positive business trip outcomes, such as securing new clients or growing revenue.
Brands like Amazon regularly use predictive analytics in their marketing tactics. Suggesting new items based on past items bought by ‘people like you’ is a tried-and-tested method to encourage spending. Human beings are surprisingly predictable and you can leverage this as a travel manager, using the same techniques.
For example, employee demographics, job grade and travel experience can be used to predict adherence to travel policy. These predictions can be used to generate savings and improve efficiency – by applying predictive behaviour modelling to employees, you can nudge the naughty and leave the nice alone.
Compliance is not the only behavioural predictive application – using algorithms to provide personalised booking experiences and auto-generated predictive itineraries is another way such applications add value.
When low-success trips are investigated, common patterns do emerge.
A study conducted by CWT revealed that, amongst 10,000 respondents, 12 per cent of all business trips are considered failed trips by the travellers themselves, mostly due to bad planning.
Analysing the reasons behind the unsuccessful trips, CWT’s data scientists have discovered three key factors affecting the percentage of successful business trips for travellers:
- Advance booking: A trip booked less than 3 days in advance has a 21 per cent chance of being unsuccessful. This reduces three-fold when booked and planned 15 days in advance.
- Number of meetings: A trip with only one meeting produces an unsatisfactory result 19 per cent of the time. Every additional meeting booked within a trip reduces the probability of an unsuccessful trip by approximately 10 per cent.
- Time spent in meetings: In 38 per cent of the unsuccessful trips, the cumulative meeting time was 4 hours or less. When that’s an hour or less, the probability of an unsuccessful trip is 28 per cent.
Predictive models for trip success (and spend value) can be incorporated into the trip approval process by looking at the above three factors.
Simply insisting that each trip consists of at least two meetings and has at least 4 hours of total meeting time can cut wasted travel by over a quarter, creating significant savings and setting up business travellers for the best chance of success.
Here, the key is to understand how travel expense correlates with the business itself. Don’t assume next year will be like this year – some parts of the business will respond to changes in the business environment and performance differently than others, and you want your predictions to be in line with business planning.
Identifying the key performance indicators for the business, correlating them with the travel expenditure in each department and using past data with matching expenditure can allow travel managers to predict the chances of reaching those KPIs. Using historical data and some statistical modelling can ensure your expenditure forecasts are more accurate.
The bottom line is that there are some smart ways you can apply predictive analytics to corporate travel. The key is to be realistic about what you’re predicting and ensuring you have the right technical skills in your team. There is no mystery to predictive analytics. People do it all the time, and travel managers should too.
This article was written by Eric Tyree, Chief Data Scientist and Michael Ryan, Managing Director, Australia / New Zealand, at Carlson Wagonlit Travel