Today, the software analytics space is more crowded than its ever been. Standard ETL-solution providers are adding analytics to their multitude of offerings. Many of these new players in the Master Data Management (MDM) field have BI platforms that combine integration, preparation, analytics and visualization with governance and security features.

    Such standard analytics processes as column dependencies, clustering, decision trees, and recommendation engines are all included in many of these software offerings. Instead of forcing clients to purchase modules on top of modules on top of modules, new software companies are creating packages that contain many built-in analytical functions. Thanks to built-in connectors, open source products like R, Python, and the WEKA collection can easily be slotted into many of ETL, MDM, BI, CI and MA software solutions, thereby reducing costs the need for expensive translation layers.

    Before going any further, I believe one of the first questions that needs to be answered in this chapter is: “What exactly is analytics?” The standard answer is that there are four different types of analytics and they are:

    • Descriptive analytics – What happened?
    • Diagnostic analytics – Why did it happen?
    • Predictive analytics – What will happen?
    • Prescriptive analytics – How can we make it happen again?

    Figure 6 contains examples of how each of these types of analytics can be utilized by an IR.

    Casino Analytics Value Escalator

    Figure 6: Analytics Value Escalator


    Diagnostic analytics is a form of advanced analytics that examines data or content to answer the question, “Why did it happen?” It attempts to understand causation and behaviors by utilizing such techniques as drill-down, data discovery, data mining and correlations. Building a decision tree atop a web user’s clickstream behavior pattern could be considered a form of diagnostic analytics as these patterns might reveal why a person clicked his or her way through a website.

    In his seminal article Predictive Analytics White Paper[i], Charles Nyce states that, “Predictive analytics is a broad term describing a variety of statistical and analytical techniques used to develop models that predict future events or behaviors. The form of these predictive models varies, depending on the behavior or event that they are predicting. Most predictive models generate a score (a patron rating, for example), with a higher score indicating a higher likelihood of the given behavior or event occurring.”

    Data mining, which is used to identify trends, patterns, and/or relationships within a data set, can then be used to develop a predictive model.82 Prediction of future events is the key here and these analyses can be used in a multitude of ways, including forecasting behavior that could lead to a competitive advantage over rivals. Gut instinct can sometimes punch you in the gut and predictive analytics can help factor in variables that are inaccessible to the human mind and often the amount of variables in an analytical problem are beyond human mental comprehension.

    Predictive analytics (or supervised learning) is the use of statistics, machine learning, data mining, and modeling to analyze current and historical facts to make predictions about future events. Said another way, it gives mere mortals the ability to predict the future like Nostradamus. In recent years, data-mining has become one of the most valuable tools for extracting and manipulating data and for establishing patterns in order to produce useful information for decision-making.

    Whether you love it or hate it, predictive analytics has already helped elect presidents, discover new energy sources, score consumer credit, assess health risks, detect fraud, and target prospective buyers. It is here to stay, and technology advances ranging from faster hardware to software that analyzes increasingly vast quantities of data are making the use of predictive analytics more creative and efficient than ever before.

    Predictive analytics is an area of data mining that deals with extracting information from data and using it to predict trends and behavioral patterns. Often the unknown event of interest is in the future, but predictive analytics can be applied to any type of unknown, whether that is in the past, the present, or the future.

    Predictive analytics uses many techniques from data mining to analyze current data to make predictions about the future, including statistics, modeling, machine learning, and artificial intelligence. For example, logistic regression can be used to turn a market basket analysis into a predictor so that a casino can understand what items are usually purchased together. Of course, the old beer and diapers story market basket wouldn’t fit for a casino, but gleaning data from the casino floor could reveal second favorite games that patrons like to play. This could be useful information when a patron is having a run of bad luck on his or her favorite game. Perhaps a marketing offer for a game he or she sometimes plays would be appreciated rather than an offer on his or her favorite game, as that might not be seen in such a positive light while the patron is in the midst of a losing run.

    For a casino, predictive analytics can also be used for CRM, collection analysis, cross-sell, customer retention, direct marketing, fraud detection, product prediction, project risk management, amongst many other things.

    Prescriptive analytics tries to optimize a key metric, such as profit, by not only anticipating what will happen, but also when it will happen and why it happens. Wikipedia states that, “Prescriptive analytics suggests decision options on how to take advantage of a future opportunity or mitigate a future risk and shows the implication of each decision option. Prescriptive analytics can continually take in new data to re-predict and re-prescribe, thus automatically improving prediction accuracy and prescribing better decision options.”[ii]

    Prescriptive analytics can ingest a mixture of structured, unstructured, and semi-structured data, and utilize business rules that can predict what lies ahead, as well as advise how to exploit this predicted future without compromising other priorities. Stream processing can add an entirely new component to prescriptive analytics for this.

    Predictive analytics utilizes the following techniques:

    • Regression
    • Linear regression
    • Discrete choice models
    • Logistic regression
    • Multinomial logistic regression
    • Probit regression
    • Time series models
    • Survival or duration analysis
    • Classification and regression tress
    • Multivariate adaptive regression splines
    • Machine learning
    • Neural networks
    • Naïve Bayes
    • K-nearest neighbors

    The analytics powerhouse SAS is finding its vaunted place atop the analytics pyramid challenged not just by their typical acronymed competitors—SAP, IBM, EMC, HDS, and the like—but also by the simpler visualization toolmakers like Tableau, Qlik, and Alteryx, who are muscling their way into the mix, with offers that include data blending and in-memory technology that allows business users to access complete datasets at the touch of a button. These solutions offer less complex analytical capabilities, but such things as market basket analysis or simple decision tree networks can be created with them and the costs associated with them can be one quarter or one fifth of what the top echelon providers charge.

    Throughout the rest of this chapter, I will break down many of the different types of analytical models that can be used to strengthen the customer experience for casino companies.

    In its conference paper How Predictive Analytics is Changing the Retail Industry[iii] from the International Conference on Management and Information Systems, the writers argue that predictive models incorporate the following steps:

    • Project Definition: Define the business objectives and desired outcomes for the project and translate them into predictive analytic objectives and tasks.
    • Exploration: Analyze source data to determine the most appropriate data and model building approach, and scope the effort.
    • Data Preparation: Select, extract, and transform data upon which to create models.
    • Model Building: Create, test, and validate models, and evaluate whether they will meet project metrics and goals.
    • Deployment: Apply model results to business decisions or processes. This ranges from sharing insights with business users to embedding models into applications to automating decisions and business processes
    • Model Management: Manage models to improve performance (i.e., accuracy), control access, promote reuse, standardize toolsets, and minimize redundant activities.

    Even though this was a paper around the subject of retail, it can be utilized for model building in the casino industry as well.


    [i] Nyce, Charles. 2007. Predictive Analytics White Paper.


    [iii] How Predictive Analytics is Changing the Retail Industry. International Conference on Management and Information Systems. September 23-24, 2016.

    © 2017 Intelligencia. All Rights Reserved.

    Please publish modules in offcanvas position.