The hospitality industry is one of the most know customer-centred businesses. Within this business a large amount of customer data is being processed. Data helps to deliver and understand the customer, the customer’s needs, wants, desires and wishes. Data mining is an automated process, which helps organisations to search through all the collected data to discover patterns and trends. (Magnini, Honeycutt, & Hodge, 2003)
Most of the data base systems used within the hospitality industry are the CRS (reservation), PMS (property), POS (sales) and loyalty programs. Here for data mining and analytics play a huge role within the industry. (Chamelian, 2015)
With the combination of these data, hoteliers can take action guest on a consistent level. With this information they can go beyond their traditional loyalty programs and understand the behaviour, choices and needs of a particular segment. This offers hotels the opportunity to identify opportunities and attract new guests. (Dragosavec, 2015)
The primary concern is the management of the existing data. This requires investments into different kind of systems, programs and hardware. And most important, trained and skilled staff who work on maintaining existing data. This is time consuming. Below some tips and tricks on use data mining effectively in the hospitality industry. (Magnini, Honeycutt, & Hodge, 2003)
#1 Match your IT priorities with an appropriate provider. See who can translate your data into valuable information.
#2 Build segmentation and predictive models. One consumer can fit into different segments. But building a suitable model and segment to fit in is key in the hospitality industry. Find a supplier who creates experienced models who strengthen the expertise of the IT department.
#3 Collect data to support the models. By collecting the accurate data, this input can lead to an increase in the value of the models.
#4 Select the appropriate tools for analysis and prediction. Instruments like genetic algorithms, neural networks and decision trees can be used for data mining in the hotel industry.
#5 Demand timely output. Check the output of the data as it varies far and wide.
#6 Refine the process. As datamining is an ongoing process it is key to continuously modify and refine the conditions of the inputs and outputs. Especially in a competitive environment.
#7 Hire a well-trained staff and a knowledgeable IT manager. It is very important for productive data mining that both the IT manager and the staff (management) are able to interpret the outcome of the data.
Moreover, there are also some limitation and boundaries to data mining. (Agganwai, 2015)
#1 Data mining analyses only data collected from existing customers. Data mining software does collect information about patterns from the guest loyalty programs, reservation and property systems. This technology does not provide information about segments which are not yet in the data base. As well information about the customers who are in competitor’s systems.
#2 Databases used in the mining process are often hotel-brand specific. Data bases do create prediction models that are brand sensitive. Marketing information can be useless if the hotel wants to predict customer demand (based on brand-portfolio).
#3 Data mining may not segment travellers by psychographic traits. Personality distribution amongst travellers are not the main input for data-mining systems. Sometimes, psychological factors influence customer purchase behaviour.
#4 Data mining does not provide information about customers’ though process. Important for the organisation is to (within data-mining), ask the customers’ needs are and what the hotel (product/service) is about. Called: conducting in-depth conversation.
Agganwai, C. C. (2015). Data Mining: The Textbook. Switzerland: Springer.
Chamelian, S. (2015). Using data mining and analytics to your hotel’s advantage. Retrieved October 2, 2016, from E Hotelier: https://ehotelier.com/insights/2015/09/09/using-data-mining-and-analytics-to-your-hotels-advantage/
Dragosavec, G. (2015, September). Big Data Analytics in Hotel Industry. Retrieved October 2, 2016, from KD Nuggets News: http://www.kdnuggets.com/2015/09/big-data-analytics-hotel-industry.html
Magnini, V. P., Honeycutt, E., & Hodge, S. (2003). Data Mining for Hotel firms: Use and limitations. Cornell University.