Whenever you use Google, Yahoo, or Bing, you have probablybecome used to seeing a short list of topic suggestions before you even finishtyping your search string. Online retailers like Amazon.com, often suggestproducts to you as you shop (as in, “People who bought this also bought…”). Whatdo think when an online retailer sends you an email suggesting it has found theproducts you are looking for (and they are a pretty close match)? What aboutwhen online movie services, like Netflix, recommend films to you based on priorviewing habits?
When websites appear to know you, and make recommendationsto you, they are using analytics that are designed to predict what you want. Analyticsmake websites smarter. The predictions and recommendations they produce save ustime and make the Web easier to use. Analytics personalize our user experienceand enhance our relationship with the content provider.
Let’s take a closer look at analytics and how they can helpimprove learning and performance.
Analytics vs. reports
Analytics should not be confused with reports. Many of usare familiar with reports produced by systems such as LMSs, HRMSs, or othersystems that we may use at work, or at home (home finance software, forexample). Reports are very useful, but they only supply us with data: lists ofitems that can be filtered and sorted.
Analytics are far more sophisticated. Analytics recognizepatterns in the data and illustrate them in ways that help us visualize whatthe data represents. Through analytics, we gain insight into how and why datapatterns are occurring. Increasingly, businesses are transforming theseinsights into predictions and recommendations that connect the right peoplewith the right content faster, and with greater accuracy.
Descriptive and predictive analytics
There are many categories of analytics, but two of the majortypes are descriptive and predictive. Descriptive analytics are used to interpretwhat has already happened. Predictive analytics are used to determine what mighthappen next.
Descriptive analytics
Many businesses and social networking services make use of descriptiveanalytics. For example, social networking services keep track of things likethe number of posts, replies, mentions, followers, likes, and friends. Theseare easy to count because they have already happened. Analytics interprets thisdata to identify the most popular content, the most influential contributors,the hottest topics, relationships, and degrees of separations between friendsor followers, and more.
Take this concept a step further. Analytics can segmentusers based on profile data to identify shared characteristics of people who haveused certain types of content and interacted with the site in certain ways. Theseinsights can be used to define rules that drive a customized social experiencewith features that list profiles you have visited recently, people who haveviewed your profile, other profiles that have been also viewed by people whoviewed yours, people you may know, and content that may be of interest to you.
Similarly, many retail businesses use analytics to countpeople who have viewed product descriptions, purchased products, opted in orout of marketing programs, bought product x after first viewing products y andz, made online and in-store purchases, and just about anything else that peopledo when visiting the site. Analytics can segment customers by profile data,purchase history, and other ways to help make product design, placement, andpricing decisions or refine marketing program terms, durations, and targetcustomers.
For example, Google offers search suggestions soon after youbegin typing. Its suggestions are based on data about how other people search,your location, your recent searches, and the words you are forming as you type.
Type the word lawnand Google may suggest things like lawnmower, lawn mower repair, and lawn service.
Delete your search string and retype the word law and you will see a new list thatprobably includes lawn mower firstfollowed by items like lawless, law and order, and law abiding citizen. Lawnmower appears in the list because of your previous search attempt.
Add the letter yto form lawy and you will see anothernew list containing lawyer, and lawyers in [your vicinity].
Google uses descriptive analytics to save you time and helpformulate the search string that will yield the results you seek.
Predictive analytics
Predictive analytics are used to determine what might happennext. Possible outcomes (predictions) are based on a set of inputs(predictors), ranked by probability (the likelihood they will happen.) Thistype of analytics is used to predict search-string suggestions, credit risk,fraud detection, health-condition risk, timing and demographics for sales andmarketing offers, at-risk students, content relevance, and many otherpredictions.
Predictive analytics use a combination of descriptive(historic) and real-time data to create models that predict user needs asaccurately as possible. There is a good deal of math and statistics involved increating prediction models. Typically, they use probability and regressionalgorithms.
Probability calculates the chances of an outcome. A zero (0)probability indicates that the outcome is impossible and a probability of one (1)means that the outcome is certain. So the probability of most things fallssomewhere between 0 and 1. For example, the probability that your coin toss willland on heads is 1/2 or 0.5. The probability that you will draw an ace from adeck of cards is 4/52 or about 0.077.
Regression analysis is a method used to estimate the expectedchanges to an outcome when one or more inputs are varied. Calculations are madeto regress down towards the normal average, or mean probability of the outcome for each set of input conditions.
In predictive analytics, three key factors may be evaluatedas inputs: (1) what is known about the content you seek; (2) what is knownabout you; and (3) what is known about others like you. Based on these three factors,a system attempts to predict what you will do next.
For example, Netflix evaluates what it knows about itsmovies. This may include how popular they are, awards they have won, their MPAArating, how they are tagged by genre, and other characteristics. It alsoevaluates what it knows about you. This may include the genres you view most, themovies you’ve already viewed, the types of movies you watch more than once, howyou rate movies, whether you tend to view movies in one sitting, and the timesof day and days of the week that you tend to watch. Finally, it evaluates otherpeople who have viewing characteristics similar to yours.
Netflix uses its predictive rating algorithms to predict themovies you are most likely to rate highly. Each row of movies you see on the menuis listed from left to right in order of your personal rating prediction. That’swhy the movies displayed on each customer’s Netflix page are different.
Applying analytics to learning and performance: three examples
The ways in which one can use analytics, predictions, andrecommendations to enhance learning and performance are limited only by ourexperience and imagination.
To get started, let’s discuss three illustrative examples:social media, knowledge management, and higher-education course selection. Thefirst two are hypothetical; the third is a real application.
Social media for learning
Let us suppose you have recently introduced a new onlineenvironment to support a community of practice for developing the leadershipskills of 2,500 front-line managers through communication and knowledgesharing. The online community enables managers to find and post articles onvarious topics to a blog, chat online about the articles and a variety of workplaceissues, “agree” or “disagree” with specific articles, posts, and replies, andfollow people whose articles and posts are of interest. A regular videointerview featuring a different executive or manager each week is posted in thecommunity site to communicate leadership values and generate discussion.
You apply descriptive analytics to interpret quantitativedata like article submissions, posts, and replies and then identify the mostrelevant and controversial topics by region, functional area, and businessunit. You use these insights to plan new video interviews and discussiontopics. You may even inform upper management of controversial topics that mayrequire guidance, clarification, or policy-making.
Your social-learning solution is designed to promote ongoingdiscussion and exchange. Analytics enable you to keep the pulse of what isimportant and relevant, and take appropriate action when needed.
Knowledge management
Let’s assume that you work for a company that manufacturesand sells products. In one of the business groups in your company, a market-researchteam continually conducts market analysis, competitive analysis, and customeranalysis. In the same business group, product-management teams design anddevelop various lines of products with features and price points geared towarddifferent types of customers. In order to be effective, your company’s salesforce needs to be knowledgeable about all of it: products, competitors, markets,and customers.
Formal courses can’t possibly keep up with the volatility ofthe information and sales people need to be in front of customers rather thanin training. So you develop a knowledge exchange where market researchers andproduct managers can post competitive information, product information, andsales materials. Sales people can search the knowledge exchange for the latestinformation needed to make the sale and indicate whether or not they foundspecific content helpful.
Your knowledge exchange is so effective that six otherbusiness groups get on board. The system scales up to six times the amount ofcontent. However, over time, some of the content becomes redundant, dated, nolonger relevant or accurate. The combination of rapid system growth and lack ofcontent “shelf-life” management will eventually result in overall degradationof the system’s value. For sales people, it will become more difficult to find theright information, expeditiously.
You implement predictive analytics to track content posts,search string entries, and content retrievals. You factor in what is knownabout the content (e.g., date published, date last updated, user rating, whopublished it, and how it is tagged); what is known about the user (e.g., businessunit, region, rating trends, and frequency of use); and how other users with similarcharacteristics use the system. All this information is run through statisticalalgorithms to generate predictive models that enable you to make searchsuggestions and rank order search results based on predictions of relevance tothe user. You also push email alerts to the user when items of predictedrelevance are posted or updated.
You apply descriptive analytics to improve shelf-lifemanagement. Publishers of content that has not been retrieved for a giventimespan or has been rated poorly are notified via email to review and updatethe content, or remove it from the site.
In this way, analytics dramatically increases the value ofyour knowledge-exchange solution to the sales force as well as to the productmanagement and market researchers who publish content, while allowing thesystem to grow significantly in scale.
Higher education course selection
While many state universities are funded based on the numberof students enrolled, Austin Peay State University in northern Tennessee isfunded based on the number of students that graduate. To assist students in courseselection, Austin Peay has developed a system called Degree Compass. It isavailable to students via a website and mobile app. Degree Compass evaluateswhat it knows about its curriculum such as degree requirements, majors, andcredits. It also evaluates what it knows about the individual who is using thesystem, including the courses she completed, her grades, standardized testscores, and high school grades. Finally, the system evaluates what it knowsabout other students from previous years such as their transcript informationand whether they graduated.
Degree Compass then provides a personalized course-rankingsystem to help students select courses that will count towards their degree. Thesystem ranks potential courses based on (a) the course’s prerequisiterequirements and relationship with the university’s general curriculum, (b) whetherit fulfills unmet requirements related to the student’s major, and (c) aprediction of the grade the student is likely to receive in the course. Acourse’s ranking is indicated by the number of stars displayed next to it. Interestingly,data show that the system correctly predicts students who will earn a C or betterin a course 90 percent of the time, grades to within 0.6 of a letter grade onaverage, and semester GPA within 0.02.
Resources in the field of learning analytics
Over the last 10 years, the application of analytics tolearning has grown.
Columbia University Teacher’s College offers a focus in learning analytics in its master’sdegree in cognitive science program.
Professional associations that sponsor conferences dedicatedto learning analytics include the Society for Learning Analytics Research (SoLAR) and the International Educational Data Mining Society (IEDMS).
The Experience API (xAPI) specification allows us to recordanything we want to track about anything users do, in any tool or system. Youcan use its tracking capabilities to supply analytics solutions with the bigdata needed to identify patterns, make predictions, and providerecommendations.
Commercial learning analytics software tools include LOCO-Analyst, Student Activity Monitor (SAM), and SNAPP. Thereare many general purpose business analytics tools that one can also use toanalyze learning data.
Conclusion
When you really think about it, it is strange thatbusinesses continue to rely on learning metrics that merely indicate whether anindividual completed and passed, completed and failed, or did not completetraining. Analytics provide boundless opportunities for us to collect and use muchmore meaningful data.
Implementing analytics solutions is not a simple task. It islikely to require specialized software and collaboration with a data analyst,perhaps a vendor, or someone in your IT department. However the opportunitiesanalytics offer are significant.
The first step is to define what it is that you want todescribe or predict. Next, identify the factors that need to be considered: whatyou know about your offerings, what you know about your user, and what you knowabout other users with similar characteristics. Then you’ll be ready to partnerwith a data analyst to explore various analytics methods.
Analyticscan provide us with powerful, detailed insight into the effectiveness of ourlearning programs, improve our ability to plan for future learning needs, andenable us to predict the success of our learners. Just as many of the websiteswe use are getting “smarter,” saving us time, and becoming more personalized,we can apply analytics to provide the same benefits to the people who use ourlearning and performance solutions.
