{"id":2683,"date":"2015-11-22T21:00:44","date_gmt":"2015-11-23T02:00:44","guid":{"rendered":"https:\/\/digital.hbs.edu\/platform-digit\/submission\/expedias-use-of-big-data-from-efficient-collection-to-wise-exploitation-for-better-customer-satisfaction\/"},"modified":"2015-11-22T21:03:43","modified_gmt":"2015-11-23T02:03:43","slug":"expedias-use-of-big-data-from-efficient-collection-to-wise-exploitation-for-better-customer-satisfaction","status":"publish","type":"hck-submission","link":"https:\/\/d3.harvard.edu\/platform-digit\/submission\/expedias-use-of-big-data-from-efficient-collection-to-wise-exploitation-for-better-customer-satisfaction\/","title":{"rendered":"Expedia\u2019s use of big data, from efficient collection to wise exploitation for better customer satisfaction"},"content":{"rendered":"

The effort of collecting data and that of making money-generating use of it are two very distinct actions for companies planning to grow from it \u2013 or even make their business-model entirely on it. That is the case of Expedia. In March 2014, Andrew Warner, Expedia\u2019s senior marketing director for Europe Middle-East & Asia (EMEA), was speaking at a technology conference in London, and opened his speech by asking the attendance: \u201cWhat the f*ck is big data?\u201d. Expedia has around 150 sites that operate in 70 countries worldwide, with around 50 million visitors a month and 200 mobile app downloads per minute \u2013 little to say Expedia collects daily massive amounts of data. In order to take advantage of this mine of information, it\u2019s been spending since 2013 at least 500 million USD per year in research and development, as well as 2 billion USD in marketing. Where does this money go into? What is the impact on Expedia\u2019s business, and what questions does it raise for the future of the company in an every day more connected, faster world market? Do the innovations these investments give to Expedia really address what customers want from Expedia in the end?<\/p>\n

Collecting data has been at the core of the online travel agent in order to differentiate itself first to brick-and-mortar travel companies, then to its digital competitors, improving the quality of its offer to the customer and the speed to bring him to satisfaction with a tailor-made trip \u2013 whether hotel and\/or flight. This gave insight to the company on the fact that if collected incorrectly, data that be more of a strategic handicap than anything else. First of all, data does not always reveal technical failures on an application: data showed only 20% of customers finalized a purchase while going all the way to the last checkout page. The explanation was a bug on the \u201cpurchase\u201d button, something data would not explain alone. Secondly, Expedia found out raw data numbers don\u2019t replace qualitative feedback \u2013 as seen in the previous point, it can even give an explanation to trends data reveal but can\u2019t explain alone. Hence, Expedia started to make extensive use of data generated by feedback loops. The third lesson drawn from Expedia\u2019s efforts to collect data is that it is much more efficient \u2013 and profitable \u2013 to only chase a few selected categories of information. Too many data requests to the customer can drive him away from the platform. That\u2019s what happened with the \u201ccompany information\u201d optional box in the checkout page before finalizing the purchase. Not a lot of people were filling it, and taking it away drove 1 million USD profits in a month\u2026.<\/p>\n

Expedia particularly focused its efforts in understanding and improving customer lifetime value. It is a tough task considering many customers who book through Expedia do not always have an account. \u201cOur industry has some commodity aspects, which can make it tempting to focus more on transactions than customers; increasing lifetime value requires a long history of customers, not transactions,\u201d explains Joe Megibow, general manager of Expedia. \u201cWe spent significant time building data sets, clusters and predictive models to determine which customers are most likely to buy. We can determine how much we are willing to spend to acquire a customer on the first transaction, and which types of transactions or campaigns have the highest probability of driving a second or third transaction. Customer lifetime value analysis also demonstrates that the cost to drive future transactions declines among loyal customers. We can spend more to acquire customers early on, but the overall cost for transactions declines as we come up with programs that build loyalty. (\u2026) We built and trained a utility model, using real-time pricing data from hoteliers and historical customer data, to predict what would be most relevant to consumers. We\u2019ve (\u2026) seen multiple percentage point increases in conversions.\u201d<\/p>\n

The biggest move of Expedia in that field is certainly its acquisition of Orbitz, in an effort to boost its mobile-phone transaction revenues. Acknowledging the diversification of devices on which travel purchases are made \u2013 from tablets to smartphones through desktops, the alliance of the two giants is much more than the aggregation of both companies\u2019 revenues – which amounts to 140 billion USD -, but rather to join forces in order to offer ever faster and more accurate results to the customer, as data gets more and more complicated every day. That is the essence of the challenge Expedia and its competitors face today: will they put up with the exponentially growing number of data available, are they going to make use of it, and are they going to respond to customer needs in the end? Is speed the main pain point for the customer? How are customer preferences relevant and person-dependent, knowing that what drove primarily customers away from brick-and-mortar travel agents to companies like Expedia was simply\u2026 cheaper prices.<\/p>\n

 <\/p>\n

 <\/p>\n

\"SuitCase\"<\/u><\/strong><\/p>\n

 <\/p>\n

Sources:<\/u><\/strong><\/p>\n