Business intelligence and big data in hospitality and tourism: a systematic literature review

Article

Accepted Version

Tables

Mariani, M., Baggio, R., Fuchs, M. and Höpken, W. (2018) Business intelligence and big data in hospitality and tourism: a systematic literature review. International Journal of Contemporary Hospitality Management, 30 (12). pp. 3514- 3554. ISSN 0959-6119 doi: https://doi.org/10.1108/IJCHM-07- 2017-0461 Available at http://centaur.reading.ac.uk/76422/

It is advisable to refer to the publisher’s version if you intend to cite from the work. See Guidance on citing .

To link to this article DOI: http://dx.doi.org/10.1108/IJCHM-07-2017-0461

Publisher: Emerald

All outputs in CentAUR are protected by Intellectual Property Rights law, including copyright law. Copyright and IPR is retained by the creators or other copyright holders. Terms and conditions for use of this material are defined in the End User Agreement . www.reading.ac.uk/centaur

CentAUR

Central Archive at the University of Reading

Reading’s research outputs online Table 1: Major components and functional subdomains within the Business Intelligence umbrella

Major Concept Acronym Short Explanation Reference Decision Support DSS Computer-based information system that Burstein and System supports decision making resulting in ranking, Holsapple, 2008; sorting, or choosing from among alternatives Sauter, 2011 Data DW Central data repository system of integrated data Kimball et al., Warehousing from one or multiple sources that stores current 2008 and historical data in one single place and format Online analytical OLAP Provides multi-dimensional analytical queries Kimball et al.,

processing encompassing data warehousing and reporting. 2008 Supports the operations of consolidation, drill- down, slicing and dicing Data Mining DM Discovers correlations and patterns in (usually Larose, 2005; Rud, large) data sets involving methods of machine 2009 learning, statistics and mathematical modelling Business BI Umbrella term comprising the domains of DW, Kimball and Ross, Intelligence OLAP and DM 2016 Descriptive - Uses data aggregation (e.g. sums, averages, Williams, 2016 Analytics percent, changes, etc.) and data mining to provide insight into the past to answer: “What has happened”? Predictive - Uses statistical and DM models to forecast the Dedić and Stanier, Analytics future and answer: “What could happen?” 2016 Prescriptive - Uses machine learning and computational Dedić and Stanier, Analytics modelling to advice on optimal outcomes and 2016; Williams, answers: “What should we do?” 2016 Big Data BD Data sets that are so large or complex that Erl et al., 2015 traditional data processing application software is inadequate to deal with them. Includes challenges, as data extraction, storage, analytics, visualization, querying, updating and information privacy

Table 2. Business Intelligence works in Hospitality and Tourism (selected works)

Type of paper Data reporting Type of data Data collection Data analysis Article (author & title) Research topic (conceptual/ Source(s) of data and & size methods techniques empirical) visualization Text-based online Latent Dirichlet review analysis using Amadio and Procaccino Allocation exploratory text mining (2016). Competitive analysis of Online reviews from Manually (one- (LDA) topic Dashboard, techniques and visual Empirical Unstructured online reviews using TripAdvisor time) model, random SWOT analysis analytics for SWOT exploratory text mining forest analysis, applied to the classification hotel industry PAM (Partitioning Around Medoids) clustering Combined web usage with Edit and content Distance Arbelaitz et al. (2013). Web mining to generate user sequence usage and content mining to Web page content navigation profiles and alignment extract knowledge for and web server log Structured and semantically enriched Empirical Automatically method, SPADE N/A modelling the users of the files of Bidasoa unstructured user interest profiles as (Sequential Bidasoa Turismo website and Turismo website input to website Pattern to adapt it optimization and Discovery using marketing Equivalence classes), Latent Dirichlet Allocation (LDA) topic model Nested mixed logit Ashiabor et al. (2007). Logit models to estimate One-time Nested and Market share models for forecasting market share of American Travel collection of Empirical Structured mixed logit plots for 5 nationwide intercity travel automobile and Survey existing models income groups demand in the United States commercial air secondary data transportation Fuzzy Model based multidimensional data Web pages for Carrasco et al. (2013). A model to solve Opinion data extraction are Dashboard, On- multidimensional data model Aggregation when Atrapalo, Booking, Structured and Automatically Explorative Data Line Analytical Empirical using the fuzzy model based on integrating eDreams, Expedia, unstructured (periodically) Analysis (EDA) Processing the semantic translation heterogeneous TripAdvisor (OLAP) information (including unstructured data)

Chen and Tsai (2016). Data Data mining framework Survey of 33 mining framework based on based on rough set directly-managed Rough set theory rough set theory to improve theory (RST) to support Empirical Structured Manually N/A stores of a restaurant (RST) location selection decisions: A location selection chain case study of a restaurant chain decisions Mining high-value family travelers for Chiang (2015). Applying data RFM model, CRM systems of online mining with a new model on Analytic airlines and travel Manually (one- customer relationship Empirical Customer survey Structured hierarchy process N/A agencies to identify time) management systems: A case (AHP), C5.0 decision rules for of airline industry in Taiwan decision tree discovering market segments Dursun and Caber (2016). Profiling hotel RFM model, self Using data mining techniques customers by Manually (one- organizing map Self organizing for profiling profitable hotel recency, frequency and Empirical CRM system Structured time) (SOM), k-means map (SOM) customers: An application of monetary (RFM) clustering RFM analysis indicators A Destination Management Fuchs et al. (2013). A Html-based web Information system knowledge destination Manually (one- application, focusing on Online- framework for tourism Customer feedback Structured and time) and Explorative Data dashboards, On- Analytical Processing Empirical sustainability: A business data (survey-based) unstructured automatically Analysis (EDA) Line Analytical (OLAP) to measure intelligence application from (periodically) Processing proportion of tourists Sweden (OLAP) with smallest ecological footprint BI-based knowledge Html-based web Fuchs et al. (2014). Big data Web search, booking Manually (one- Explorative Data infrastructure Structured and application, analytics for knowledge and feedback data time) and Analysis (EDA) implemented at the Empirical unstructured dashboards, On- generation in tourism (e.g., survey-based, and machine Swedish mountain Line Analytical destinations - A case from destination, Åre and user-generated automatically learning (Support Processing Sweden examples of use by content) (periodically) Vector Machine, (OLAP) tourism managers Naïve Bayes, Nearest Neighbor) Examines how Holland et al. (2016). The role consumers search for and impact of comparison Click-stream panel airline tickets based on a Manually (one- Consideration set websites on the consumer Empirical data by ComScore Structured N/A comparative analysis of time) theory search process in the US and the US and German German airline markets markets Explorative Data Analysis (EDA) A novel approach for and data mining Html-based web BI-based cross-process Web search, booking Höpken et al. (2015). Business manually (one- techniques application, knowledge and feedback data intelligence for cross-process Empirical and Structured and time) and (Decision Trees, dashboards, On- extraction and decision (e.g., survey-based, knowledge extraction at conceptual unstructured automatically Association Rule Line Analytical support for tourism user-generated tourism destinations (periodically) Mining); Multi- Processing destinations content) dimensional data (OLAP)

warehouse modelling Hsieh (2011). Employing a A recommendation recommendation expert system Expert System for travel Online (student) based on mental accounting agencies based on survey about travel Manually (one- Back propagation and artificial neural networks mental accounting and Empirical Structured N/A motivations and final time) neural networks into mining business artificial neural decision making intelligence for study abroad's networks P/S recommendations* An Expert System Hsieh (2009). Applying an Self-organizing platform addresses expert system into constructing feature map customer’s value Online customer Automatically customer's value expansion and Empirical Structured neural network N/A analysis based on survey (periodically) prediction model based on AI for cluster artificial intelligence techniques in leisure industry analysis

A tool that assists travel Kisilevich et al. (2013). A GIS- OpenStreetMap data Multi- intermediaries to MDS component based decision support system (public), Private data Automatically dimensional acquire missing for exploratory for hotel room rate estimation by a hotel brokerage (periodically) scaling (MDS); strategic information Empirical Structured data and temporal price prediction: static: names of and manually Voronoi about hotels to leverage Analysis and The hotel brokers' context hotels, internal IDs, (one-time) tessellation profitable deals. The location coordinates, partitioning; GIS-based DSS estimates room rates hotel facilities, room additive Graphs to using hotel and location amenities, regression with visualize price characteristics hotel categories. isotonic estimation Dynamic: room regression; results prices for one night Locally customers received Weighted during their search, Learning with date of search, date Linear of order Regression; LibSVM nu- SVR; Multilayer Perceptron (ANN) Assessment of 23 hoteliers’ Unstructured In-depth awareness and Köseoglu et al. (2016). knowledge and interview knowledge about N/A N/A Competitive intelligence Empirical awareness about competitive intelligence practices in hotels competitive efforts in the hotel intelligence industry Combines machine Kwok and Yu (2016). learning and human 2,654 Facebook Taxonomy of Facebook intelligence to analyze messages Machine learning Taxonomy of Unstructured Automatically/ messages in business-to- Facebook messages Empirical initiated by 26 (support vector Facebook and structured manually consumer communications: initiated by hospitality hospitality machines) message types What really works? companies companies

Identification of Unsupervised Li et al. (2015). Identifying emergent hotel features feature extraction 118,000 online emerging hotel preferences by extracting frequent Automatically by frequent Empirical reviews from Unstructured N/A using Emerging Pattern Mining keywords from online (one-time) keywords, TripAdvisor technique reviews emerging pattern mining (EPM) Machine learning A passively Confusion methods estimate trip collected long- Lu and Zhang (2015). Imputing matrices from purposes for long- distance trip dataset Manually (one- Decision tree and trip purposes for long-distance Empirical Structured trip purpose distance passenger is simulated from the time) meta-learning travel imputation travel 1995 American models Travel Survey Heterogeneous including the travel Pre-processing: blogs, webpages, web content travelogues and mining, language Studying online image travel reviews about detection, user’s of Barcelona as Data was Marine-Roig and Anton Clavé Barcelona hometown, transmitted via social extracted (2015). Tourism analytics with cleaning, Tables created media through the Unstructured automatically massive user-generated Empirical debugging. through word analysis of more than through Offline content: A case study of Heterogeneous count 100,000 relevant travel Explorer Processing: Barcelona including the travel blogs and online travel Enterprise parser settings blogs, webpages, reviews and travelogues and categorizations travel reviews about through Site Barcelona (250,000 Content Analyzer pages) Challenges and

opportunities to collect large volumes of data Pope et al. (2009). Conceptual from airline websites framework for collecting online N/A N/A N/A N/A N/A and travel agencies are airline pricing data: Conceptual discussed. Research Challenges, opportunities, and questions are preliminary results highlighted that can be investigated with this type of data. Industry Primary survey Semi-structured stakeholders’ data from 68 interview Guidelines for the Ritchie and Ritchie (2002). A establishment of a knowledge needs individuals framework for an industry comprehensive and current use of N/A N/A Empirical supported destination destination marketing research & marketing information system information system intelligence Secondary data (travel surveys) (DMIS) (Inter-)National Travel Survey Yelp is existing K-Nearest Illustrative A description of the data set; Neighbor User examples for Rossetti et al. (2016). Yelp Data set topic model method Structured and TripAdvisor Based (KNN- selected Topics Analyzing user reviews in Empirical Challenge; with application focus unstructured automatically UB), K-Nearest related to multi- tourism with topic models TripAdvisor Dataset on the tourism domain collected by Neighbor Item criteria crawler Based dimensions (KNN-IB), Probabilistic Matrix Factorization (PMF) Extraction of features Pathfinder from hotel reviews and network scaling, Sánchez-Franco et al. (2016). analysis of their 19,318 hotel reviews principal Online Customer Service Structured and Automatically relationship with guests’ Empirical from 2014 to 2015 component N/A Reviews in Urban Hotels: A unstructured (one-time) hotel rating in the online from booking.com analysis (PCA), Data Mining Approach travel agencies linear mixed- environment effects regression Keypoint detection (SIFT keypoint detector) and Presents algorithms and matching (by results as a step towards approximate reconstructed Snavely et al. (2008). Modeling 3D modeling of the Automatically nearest neighbors scenes and photo Large sets of the world from internet photo world’s well- Empirical Flickr downloaded from (ANN) kd-tree); connectivity image data collections photographed sites, Flickr Structure for graphs for 11 cities, and landscapes motion (to sites from Internet imagery recover camera parameters); geo-registration (by digital elevation maps) Market Basket Analysis to identify and predict the purchasing behavior 56,906 guest sales Solnet et al. (2016). An of customers based on records from a untapped gold mine? Exploring Automatically multivariate logit their expenditure Empirical luxury hotel group in Structured N/A the potential of market basket (one-time) model patterns in order to Australia from 2009 analysis to grow hotel revenue determine the most to 2014 attractive additional products and services Attention- Sun et al. (2016). Chinese Identification of critical interest-desire- Customers’ Evaluation of attributes that Survey data from 25 Empirical Structured Manually action (AIDA) N/A Travel Website Quality: A influence quality levels individuals model, C4.5 Decision-Tree Analysis of a customer’s travel decision tree agency’s website experience

Tseng and Won (2016). Explorative data Proposes a design of Integrating multiple analysis (EDA) Dashboards, On- sales force support recommendation schemes for and data mining Line Analytical (SFS) system with Empirical N/A N/A N/A designing sales force support (e.g. sequential Processing business intelligence system: A travel agency pattern (OLAP) methodologies example discovery) 17,496 Bluetooth Spatiotemporal tourism Versichele et al. (2014). Pattern devices being behavior by mining of mining in tourist attraction detected over A-priori association rules in Visit pattern visits through association rule Empirical 235,597 time Structured Automatically association rule tourist attraction visits maps learning on Bluetooth tracking intervals by 15 mining based on Bluetooth data: A case study of Ghent Bluetooth sensors in tracking methodology Ghent in 2015 Identification of major factors determining the Monthly hotel hotel occupancy rate occupancy rate time Wu et al. (2010). Data mining and incorporation of series for each Independent for hotel occupancy rate: An these factors to Empirical district of Structured Manually component N/A independent component decompose hotel Hong Kong from analysis (ICA) analysis approach occupancy rates and January 1996 to May examine the effect of 2009 each factor on the hotel occupancy rate Application of twice- learning framework On-site surveys in Twice-learning Zhang and Huang (2015). to predict tourists’ travel Nanjing, China, framework, Mining tourist motive for motives from tourists’ Empirical fromOctober to Structured Manually neural networks, N/A marketing development via external and internal November 2012 with C4.5 decision twice-learning features, useful for 121 responses tree, Naïve Bayes targeted marketing strategy development Location information Gazetteer-based extraction from user- location 80,384 travelogues Zhu et al. (2016). Get into the generated travelogues, detection, related to tourist spirit of a location by mining examining contents and Empirical Unstructured Manually semantic N/A destinations in the user-generated travelogues structures of correlation United States travelogues, as well as detection by their interplay natural language parsing techniques, location concept network by PLSA

Table 3. Big Data works in Hospitality and Tourism (selected works; in “type of data and size” an asterisk indicates large quantities of data, > 100 000 records)

Type of paper Data Data reporting Type of data Data analysis Article (author and title) Research topic (conceptual/ Sources of data collection and and size techniques empirical) methods visualization Proposes social context

mobile (SoCoMo) Buhalis and Foerste (2015). marketing as a new SoCoMo marketing for travel framework that enables Conceptual N/A N/A N/A N/A N/A and tourism: Empowering co- marketers to increase creation of value value for all stakeholders at the destination Explores what visitors

learn about the history Carter (2016). Where are the of the enslaved on two TripAdvisor visitor Web Word frequency enslaved?: TripAdvisor and the tours (Laura and Oak reviews (Laura and (manual) and words Empirical Unstructured Standard tables narrative landscapes of Valley) and how they the Oak Alley scraping associations in southern plantation museums participate in the museums, USA) reviews

narrative construction of the plantation

Dolnicar and Ring (2014). Critical review of Literature Tourism marketing research: tourism marketing N/A N/A N/A N/A N/A review Past, present and future research

Presents a knowledge Data On-Line Fuchs et al. (2014). Big data infrastructure Web search, booking Warehouse Analytical analytics for knowledge implemented at the and feedback data (DW) Processing Structured and Html-based generation in tourism Swedish mountain Empirical (e.g., survey-based, including (OLAP); Support unstructured web application destinations - A case from tourism destination, Åre user-generated Facts and Vector Machines Sweden and examples of use by content) Dimensions (SVM), Naïve tourism managers Tables Bayes (NB) and K-Nearest Neighbor (KNN)

Natural Describes OpeNER, a Language NLP platform applied to Online reviews from Processing: the hospitality domain García-Pablos et al. (2016). Zoover and Web Named Entity to automatically process Empirical Unstructured Standard tables Automatic analysis of textual HolidayCheck crawler Recognition, customer-generated hotel reviews Sentiment textual content Analysis and Opinion Mining

Use of photo-sharing García-Palomares et al. (2015). services for identifying Identification of tourist hot Unstructured Panoramio Density graphs, Standard tables and analyzing the main spots based on social networks: website API spatial and Anselin tourist attractions in Empirical Panoramio photos (*) A comparative analysis of + ArcGIS autocorrelation Local Moran's I eight major European european metropolises using graph cities photo-sharing services and GIS Defines smart tourism, sheds light on current Gretzel et al. (2015). Smart smart tourism trends, tourism: Foundations and and lays out its Conceptual N/A N/A N/A N/A N/A developments technological and business foundations

10 Google Analytics Google analytics Basic tables of website traffic indicators variables collected Simple descriptive Gunter and Önder (2016). VAR model from the Viennese on a monthly basis Structured access to statistics Forecasting city arrivals with Empirical class: BVAR, DMO website are used over the period Google google analytics FAVAR, to predict actual tourist August 2008- analytics BFAVAR. arrivals to Vienna October 2014 Develops a probabilistic

topic model leveraging individual travel history He et al. (2016). Travel- and social influence of Structured travel Access to a Basic tables of package recommendations co travelers to capture Structured Empirical records on travel private Biggs sampling descriptive leveraging social influence of personal interests and packages company statistics different relationship types propose a recommendation database method to utilize the proposed model Basic tables of Jackson (2016). Prediction, descriptive explanation and big(ger) data: Uses ‘automatic linear Automatic linear statistics and A middle way to measuring modelling’ that can cope Structured modelling and graphs and modelling the perceived with big data and Empirical (responses from Structured Survey preparation stemming from success of a volunteer tourism presents the results as questionnaire) through IBM automatic sustainability campaign based visualizations SPSS linear on ‘nudging’ modelling (IBM SPSS)

BuzzMonit oring BuzzMonitoring Internal sources including the Mostly (Types and (emails, counselling following Design of an analysis unstructured proportion data, bulletin modules: NLP, model for the top (e.g., data from of No table nor Kong and Song (2016). A information, after data clustering, Korean travel agency to emails, social keywords graphs study on customer feedback of use comments/ text help the company Empirical media from the stemming from tourism service using social big evaluations) and summarization, improve customer networks) and extracted the Buzz data external sources sentiment satisfaction and service several data are Monitoring (Twitter, Facebook, analysis, quality structured (e.g., digitized to OnlineNews, Blog, structure data bulleting info) analyze Community) incidents joinder. and phenomena) Trends in Hong Kong outbound tourism in Data mining, Law et al. (2011). Identifying Historical terms of Tourism behavior Survey association rules, changes and trends in Hong Empirical domestic Tables Future trip intentions survey data questionnaire contrast set Kong outbound tourism Surveys Travel destinations mining Motivation to travel. Explores how Italian Data parser and Tables created regional Destination analyzer through data Management Overall number of calculating per analyzer Mariani et al. (2016). Facebook Organisations (DMOs) Data Facebook posts post statistics module. as a destination marketing tool: strategically employ extractor posted on the official Structured Graphs created Evidence from Italian regional Facebook to promote Empirical based on Italian regional (*) through the destination management and market their Facebook DMOs’ Facebook data visualizer organizations destinations, and APIs pages module improves on the current metrics for capturing user engagement Pre-processing: web content Studying the online mining, language image of Barcelona as Data was detection, user’s transmitted via social Marine-Roig and Anton Clavé extracted hometown, media through the Heterogeneous (2015). Tourism analytics with through cleaning, Tables created analysis of more than including the travel Unstructured massive user-generated Empirical Offline debugging. through word 100,000 relevant travel (*) content: A case study of blogs, webpages, Explorer count blogs and online travel Processing: Barcelona travelogues and Enterprise reviews travel reviews about parser settings (OEE). (OTRs) written in Barcelona (250,000 and English pages) categorizations through Site Content Analyzer

Grey 2-tuple Mi et al. (2014). A new method linguistic for evaluating tour online Evaluation of online Reviews from Web Empirical Unstructured evaluation Standard tables review based on grey 2-tuple reviews tourism website crawler (expert linguistic evaluations) Language detection (Google Mocanu et al. (2013). Survey on worldwide Structured and Chromium The twitter of babel: Mapping linguistic indicators and Large-scale dataset Maps + charts Empirical unstructured Twitter API Compact world languages through trends through of geotagged tweets and tables (*) Language microblogging platforms Detector) - Geographical analyses

Structured: Noguchi et al. (2016). Conceptual, Presents technology for app’s usage Advanced, high-performance application Smartphone From app Clustering Maps + charts analyzing data and logs, location big data technology and trial design, case application logs analysis and tables location data data, and validation study individual

Kernel-density Explores the Orellana et al (2012). function properties of the Exploring visitor movement Global Positioning Structured Recording classification and GIS + standard collective movement of Empirical patterns in natural recreational System tracking data (GPS data ) of GPS data Generalized tables visitors in recreational areas Sequential natural areas Patterns

Identification of resident, tourist Tastes of individuals, Structured: and unknown, Paldino et al. (2015). and what metadata from statistical Maps + charts Urban magnetism through the attracts them to live in a Empirical Geo-tagged photos Flickr API photos analysis, network and tables lens of geo-tagged photography particular city or spend (*) analysis vacation there. (origin/destinatio n) Word frequency, Park et al. (2016). Twitter API Charts, tables, Analysis social media Tweets containing Unstructured/ content analysis, Using twitter data for cruise Empirical and Web network data on cruise tourism search words structured and network tourism marketing and research scraping diagrams analysis

Measure Statistical Anonymized space-time tracking data analyses, ArcGIS Raun et al. (2016). roaming data of the From to analyze, monitor and for spatial Charts, tables, Measuring tourism destinations Empirical foreign mobile Structured telcom compare destinations analyses, binary maps using mobile tracking data phone call detail operator based on data describing logistic records actual visits regression

Apply semantic web and big data techniques to Shi et al. (2016). help collect data, and Applying semantic web and big implement platform and Questionnaire + Structural data techniques to construct a Structured/ Unknown questionnaire design to Empirical User Generated equation model, Charts, tables, balance model referring to unstructured UGC construct stakeholder Content (reviews) path analysis stakeholders of tourism balance model for intangible cultural heritage tourism intangible cultural heritage

Characterize geographical Su et al. (2016). preferences Characterizing geographical of international tourists preferences of international and Metadata online Statistical and Charts, tables, Empirical Structured Flickr API tourists and the local influential quantify local influential geotagged photos spatial analyses maps factors in china using geo- factors of tourists’ tagged photos on social media destination preferences across time and space and origins Design of an IoT system personal sensors, open data, and participatory Integration of Internet of Sun et al. (2016). sensing to enhance Things (IoT) Internet of things and big data Conceptual + the services in the and big data analytics N/A N/A N/A N/A analytics for smart and case study area of tourism and for smart connected connected communities cultural heritage communities with a Context- Aware Recommendation System

Examine the general geospatial demand for Supak et al. (2015). overnight recreation on National Recreation Geospatial analytics for federal lands prior to the Reservation Service Structured Statistical and Charts, tables, federally managed tourism Empirical DB access 2008 recession and the reservations (*) spatial analyses maps destinations and their demand specific geospatial database markets demand for national park regions

Tang et al. (2016). Study related to spatial API from Statistical, spatial Charts, tables, Spatial network of urban tourist network of tourist flows Geotagged Structured Empirical Sina and network maps, network flow in Xi’an based on and its structure in the microblog posts (*) Microblog. analyses diagrams microblog big data urban areas Discuss evolution and Wang et al. (2015). future developments of Revenue management: revenue management Conceptual N/A N/A N/A N/A N/A Progress, challenges, and and use of big data research prospects analytics

Online posted photos are used to estimate visitation rates and Empirical datasets travelers’ origins. that Wood et al. (2013). compare quantified visitation Using social media to quantify Structured Dataset + Statistical and Charts, tables, to empirical data Empirical to 836 sites in 31 nature-based tourism and (*) Flickr API spatial analyse maps showing that crowd- countries around the recreation sourced information can world + Flickr serve as reliable metadata proxy for empirical visitation rates Demonstrate the value of website traffic data in Yang et al. (2014). predicting demand for Google Website traffic data Statistical and Predicting hotel demand using hotel rooms at a analytics + Empirical and local hotel room Structured time series Charts, tables destination marketing destination, and standard demand data forecasts organization's web traffic data potentially future data revenue and performance Yang et al. (2016). Use remote-sensing The big data analysis of land images Land use Landsat satellite use evolution and its ecological to analyze the land use Pictures + Landsat DB temporal Charts, tables, Empirical high-definition security responses in silver evolution metadata (*) statistical maps images beach of china by the clustering and to evaluate its analysis of spatial patterns ecological security