In-Depth: Edward Nevraumont, senior director - customer loyalty, Expedia on predictive analytics, and using the same to mine and analyse the data gathered from web traffic and bookings on a website.

Technological breakthroughs have provided the ability to manage and make sense of vast amounts of hitherto unrelated data.

Several sectors including the travel industry are now leveraging this data through business analytics, according to SAS, a specialist in this arena. There are quite a few facets of this discipline. Companies are using customer loyalty programmes and predictive modeling techniques to identify and retain the most profitable customers.

Also, quite a few have modeled their business and distributed analytic tools so that every property can maximise revenue not only from hotel rooms and rates, but also from other amenities. Overall, such companies are using sophisticated data-collection technology and analysis methods to wring every last drop of value from their most strategic business processes. Plus, they understand what motivates customers and makes them profitable.

As far as predictive analytics is concerned, it is about extracting information from data and using it to anticipate future trends and behaviour patterns. This is based on a variety of techniques from statistics and data mining.

According to SAS, predictive modeling uses a variety of analytical techniques to make estimates about the future based on current and historical data. These predictions are expressed as a likelihood that a particular event, opportunity, or behaviour will take place. Predictive modeling can be used in making increasingly effective and individualised decisions about the treatment of customers.

These models analyse the customers' past performance in order to assess how likely a customer is to exhibit a specific behaviour or respond to a specific offer.

Assessing profitability of customers

A company like Expedia says predictive analytics helps in prioritising projects and investment in resources with expected revenue and profitability impacts.

Talking to EyeforTravel about the utility of predictive analytics as part of the group's advanced data management strategies, Edward Nevraumont, senior director - customer loyalty, Expedia, says one of the ways in which the group is involved is for the analysis of the profitability of different types of customers.

Explaining the structure, Nevraumont said, "At Expedia Joe Megibow  (VP, Global Analytics and Optimisation at Expedia.com ) runs a very strong analytics programme that is built on a strong foundation of data warehousing – I believe we will have several hundreds of terabytes managed by FY11, most of this in a clustered DB2 instance that is accessed throughout the company.  We literally run our business by these numbers and have a team of about 30 to 40 analysts that maintain dashboards, write custom SQL queries and do all sorts of structured ad hoc analyses." 

The group also has a smaller team that builds predictive models that complement these types of analyses. 

These models really come in two basic types – one for long term planning and strategic analyses (such as customer segmentation analyses) and another for more tactical marketing programmes  (such as website personalisation).

"I have been directly involved in many of these efforts and am leading a needs-based segmentation effort that we will use to – among other things, analyse the profitability of different types of customers.  We'll use this to tailor our product and marketing mix so that we provide the right offer for the most desirable customers," said Nevraumont, who is scheduled to speak at the EyeforTravel's Customer Centric Strategies in Travel conference, to be held in Atlanta next year (Jan 26-27, 2011).

Understanding customers

As far as applications of predictive modeling for optimising customer relationships is concerned, the travel industry is looking at measuring and managing the asset value of their customer relationships. Other applications include personalising the way customer relationships are being managed and also detecting any significant change in customer behaviour that may indicate a service or retention issue.

Expedia acknowledges the usage of predictive analytics to mine and analyse the data gathered from web traffic and bookings on a website.

"Anything that helps us understand the customer at a deep level so that we can provide them the best offer that meets their needs is something that we're going to invest in. In particular, my team has invested in models that try to predict long term behaviour based on what customers are doing on our website today.  From this we can generate an alert that tells us if a customer's behaviour has changed for better or for worse.  If there's a problem, we can try to intervene – either with a special offer via email or potentially with direct customer contact for our Elite customers who are very important to us," Nevraumont said.

One of the most useful applications of business intelligence is developing effective customer retention solutions and reducing costs by identifying the greatest number of customers likely to churn within a small percentage of your customer base. Predictive model tells you which new customers are likely to return and which are probably one-timers.

Regarding the latest trends as far as customer retention is concerned, Nevraumont said, "We study this closely and have several predictive models based on RFM (recency, frequency and monetary) statistics.  We've found that these measures are very good predictors of the propensity of a customer to shop with us in the future and we provide goals within our organisation to make sure these measures are what we want them to be."

Behaviour analytics

Behaviour analytics helps online travel companies in understanding and predicting their customers' desires and to more effectively serve relevant content and products in real time, ultimately increasing satisfaction and conversion.

For example, if a customer is searching for a hotel in a gateway city for a two-night midweek stay, this is likely to be a business customer that favours certain types of hotels and is focused on making a quick purchase decision without the disrupting of ads. Behavioural analytics helps to initially segment and understand certain customer groups and then anticipate new customers needs when they display similar behaviour on the site. The sort order for hotels is a critical element of providing relevant hotels to customers.

The hotel sort order at Expedia has benefited from years of development and utilises sophisticated algorithms which include behavioural data to display the most relevant hotels to customers.

On how behaviour analytics helps in segment and understand certain customer groups and then anticipate new customers needs, Nevraumont said, "We follow a needs+ segmentation methodology that separates a customer's attitude (value / convenience) from their situation (business / leisure)."

Edward Nevraumont, senior director - customer loyalty, Expedia is scheduled to speak at the EyeforTravel's Customer Centric Strategies in Travel conference, to be held in Atlanta next year (Jan 26-27, 2011).

For more info, click here: http://events.eyefortravel.com/crm-loyalty/agenda.asp

Or contact:
Marco Saio, Global Events Director
EyeforTravel
Direct line: +44 207 375 7219
Email: marco@eyefortravel.com