While descriptive and diagnostic analytics both employ a reactive measure for strategic planning as it provides analysis only after certain events have occurred, predictive analytics is a level above the other two as it can predict the future trends by analyzing historical relationships between multiple variables.
Predictive retail analytics uses complex statistical tools and emerging technologies such as machine learning and data mining to forecast future trends. It allows retailers to predict customer behavior and estimate what kind of products will become popular in the upcoming season so that they can plan and strategize beforehand.
For instance, predictive models can determine which customers are unhappy with the brand and are likely to defect. Based on such insights, the retailers can then provide offers and incentives to retain the customers. The goal is to go beyond knowing what has happened to providing a best assessment of what will happen in the future.
Product developers can add predictive capabilities to existing solutions to increase value to the customer. Companies also use predictive analytics to create more accurate forecasts, such as forecasting the demand for electricity on the electrical grid. These forecasts enable resource planning (for example, scheduling of various power plants), to be done more effectively.
To extract value from big data, businesses apply algorithms to large data sets using tools such as Hadoop and Spark. The data sources might consist of transactional databases, equipment log files, images, video, audio, sensor, or other types of data. Innovation often comes from combining data from several sources.
With all this data, tools are necessary to extract insights and trends. Machine learning techniques are used to find patterns in data and to build models that predict future outcomes. A variety of machine learning algorithms are available, including linear and nonlinear regression, neural networks, support vector machines, decision trees, and other algorithms.
Product developers can add predictive capabilities to existing solutions to increase value to the customer. Companies also use predictive analytics to create more accurate forecasts, such as forecasting the demand for electricity on the electrical grid. These forecasts enable resource planning (for example, scheduling of various power plants), to be done more effectively.
To extract value from big data, businesses apply algorithms to large data sets using tools such as Hadoop and Spark. The data sources might consist of transactional databases, equipment log files, images, video, audio, sensor, or other types of data. Innovation often comes from combining data from several sources.
With all this data, tools are necessary to extract insights and trends. Machine learning techniques are used to find patterns in data and to build models that predict future outcomes. A variety of machine learning algorithms are available, including linear and nonlinear regression, neural networks, support vector machines, decision trees, and other algorithms.
How Predictive Analytics Works
Predictive analytics starts with a business goal: to use data to reduce waste, save time, or cut costs. The process harnesses heterogeneous, often massive, data sets into models that can generate clear, actionable outcomes to support achieving that goal, such as less stocked inventory, and manufactured product that meets specifications. In recent times, supervised machine learning techniques are used to predict a future value.
Though predictive analytics has been around for decades, it's a technology whose time has come. More and more organizations are turning to predictive analytics to increase their bottom line and competitive advantage.
Why now?
- Growing volumes and types of data, and more interest in using data to produce valuable insights.
- Faster, cheaper computers.
- Easier-to-use software.
- Tougher economic conditions and a need for competitive differentiation.
With interactive and easy-to-use software becoming more prevalent, predictive analytics is no longer just the domain of mathematicians and statisticians. Business analysts and line-of-business experts are using these technologies. Organizations are turning to predictive analytics to help solve difficult problems and uncover new opportunities. Common uses include:
Optimizing Marketing Campaigns: Predictive analytics are used to determine customer responses or purchases, as well as promote cross-sell opportunities. Predictive models help businesses attract, retain and grow their most profitable customers.
Improving Operations: Many companies use predictive models to forecast inventory and manage resources. Predictive analytics enables organizations to function more efficiently.
Reducing Risk: Credit scores are used to assess a buyer’s likelihood of default for purchases and are a well-known example of predictive analytics. A credit score is a number generated by a predictive model that incorporates all data relevant to a person’s credit worthiness.
With predictive analytics, you can go beyond learning what happened and why to discovering insights about the future.
Have your company, for example, developed a customer lifetime value (CLTV) measure? That’s using predictive analytics to determine how much a customer will buy from the company over time. Do you have a “next best offer” or product recommendation capability?
That’s an analytical prediction of the product or service that your customer is most likely to buy next. Have you made a forecast of next quarter’s sales? Used digital marketing models to determine what ad to place on what publisher’s site? All of these are forms of predictive analytics.
Predictive analytics are gaining in popularity, but what do you—a manager, not an analyst—really need to know in order to interpret results and make better decisions? How do your data scientists do what they do? Let’s talk about each of these.
The Data: Lack of good data is the most common barrier to organizations seeking to employ predictive analytics. To make predictions about what customers will buy in the future, for example, you need to have good data on who they are buying (which may require a loyalty program, or at least a lot of analysis of their credit cards), what they have bought in the past, the attributes of those products (attribute-based predictions are often more accurate than the “people who buy this also buy this” type of model), and perhaps some demographic attributes of the customer (age, gender, residential location, socioeconomic status, etc.).
Predictive analytics are gaining in popularity, but what do you—a manager, not an analyst—really need to know in order to interpret results and make better decisions? How do your data scientists do what they do? Let’s talk about each of these.
The Data: Lack of good data is the most common barrier to organizations seeking to employ predictive analytics. To make predictions about what customers will buy in the future, for example, you need to have good data on who they are buying (which may require a loyalty program, or at least a lot of analysis of their credit cards), what they have bought in the past, the attributes of those products (attribute-based predictions are often more accurate than the “people who buy this also buy this” type of model), and perhaps some demographic attributes of the customer (age, gender, residential location, socioeconomic status, etc.).
If you have multiple channels or customer touch points, you need to make sure that they capture data on customer purchases in the same way your previous channels did.
The Statistics: Regression analysis in its various forms is the primary tool that organizations use for predictive analytics. It works like this in general: an analyst hypothesizes that a set of independent variables (say, gender, income, visits to a website) are statistically correlated with the purchase of a product for a sample of customers.
The Statistics: Regression analysis in its various forms is the primary tool that organizations use for predictive analytics. It works like this in general: an analyst hypothesizes that a set of independent variables (say, gender, income, visits to a website) are statistically correlated with the purchase of a product for a sample of customers.
The analyst performs a regression analysis to see just how correlated each variable is; this usually requires some iteration to find the right combination of variables and the best model. Let’s say that the analyst succeeds and finds that each variable in the model is important in explaining the product purchase, and together the variables explain a lot of variation in the product’s sales.
Using that regression equation, the analyst can then use the regression coefficients—the degree to which each variable affects the purchase behavior—to create a score predicting the likelihood of the purchase. It’s quite likely that the high scoring customers will want to buy the product—assuming the analyst did the statistical work well and that the data were of good quality.
The Assumptions: That brings us to the other key factor in any predictive model—the assumptions that underlie it. Every model has them, and it’s important to know what they are and monitor whether they are still true. The big assumption in predictive analytics is that the future will continue to be like the past.
The Assumptions: That brings us to the other key factor in any predictive model—the assumptions that underlie it. Every model has them, and it’s important to know what they are and monitor whether they are still true. The big assumption in predictive analytics is that the future will continue to be like the past.
So What Could Make Assumptions Invalid?
The most common reason is time. If your model was created several years ago, it may no longer accurately predict current behavior. The greater the elapsed time, the more likely customer behavior has changed. Some Netflix predictive models, for example, that were created on early Internet users had to be retired because later Internet users were substantially different. The pioneers were more technically-focused and relatively young; later users were essentially everyone.
Another reason a predictive model’s assumptions may no longer be valid is if the analyst didn’t include a key variable in the model, and that variable has changed substantially over time. A great example here is the financial crisis of 2008-9, caused largely by invalid models predicting how likely mortgage customers were to repay their loans.
The models didn’t include the possibility that housing prices might stop rising, and even that they might fall. When they did start falling, it turned out that the models became poor predictors of mortgage repayment. In essence, the fact that housing prices would always rise was a hidden assumption in the models.
Since faulty or obsolete assumptions can clearly bring down whole banks and even (nearly!) whole economies, it’s pretty important that they be carefully examined. Managers should always ask analysts what the key assumptions are, and what would have to happen for them to no longer be valid. And both managers and analysts should continually monitor the world to see if key factors involved in assumptions might have changed over time.
With these fundamentals in mind, here are a few good questions to ask your analysts:
What Assumptions Are Behind Your Analysis?
Are there any conditions that would make your assumptions invalid?
Even with those cautions, it’s still pretty amazing that one can use analytics to predict the future. All you have to do is gather the right data, do the right type of statistical model, and be careful of our assumptions.
In practice, prescriptive analytics can continually and automatically process new data to improve the accuracy of predictions and provide better decision options. The effectiveness of predictive analytics also depends on how well the decision model captures the impact of the decisions being analyzed.
Businesses with an eye on the future want to know more than just what happened in the past. “Scoreboards” (most analytics tools and tracking) don’t tell you what the score will be.
Since faulty or obsolete assumptions can clearly bring down whole banks and even (nearly!) whole economies, it’s pretty important that they be carefully examined. Managers should always ask analysts what the key assumptions are, and what would have to happen for them to no longer be valid. And both managers and analysts should continually monitor the world to see if key factors involved in assumptions might have changed over time.
With these fundamentals in mind, here are a few good questions to ask your analysts:
- Can you tell me something about the source of data you used in your analysis?
- Are you sure the sample data are representative of the population?
- Are there any outliers in your data distribution? How did they affect the results?
What Assumptions Are Behind Your Analysis?
Are there any conditions that would make your assumptions invalid?
Even with those cautions, it’s still pretty amazing that one can use analytics to predict the future. All you have to do is gather the right data, do the right type of statistical model, and be careful of our assumptions.
In practice, prescriptive analytics can continually and automatically process new data to improve the accuracy of predictions and provide better decision options. The effectiveness of predictive analytics also depends on how well the decision model captures the impact of the decisions being analyzed.
Businesses with an eye on the future want to know more than just what happened in the past. “Scoreboards” (most analytics tools and tracking) don’t tell you what the score will be.
Predictive Analytics Applications For Marketing:
Predictive Modeling for Customer Behavior-Predicting customer behavior and preferences is the hallmark of companies like Amazon and eBay, but the technology is becoming increasingly accessible and relevant for smaller companies as well.
Creating a complete catalog of predictive models would be an extensive and cumbersome process, but there are a number of relatively simple model types that apply well in the marketing domain. Silicon Valley-based predictive marketing company AgilOne identifies three primary classes of predictive models:
Cluster Models (Segments) – Used for customer segmentation; algorithms segment target groups based on numerous variables, everything from demographics to average order total. Common cluster models include behavioral clustering, product based clustering (also called category based clustering), and brand-based clustering.
Propensity Models (Predictions) – Used for giving “true” predictions about customer behavior. Common models include predictive lifetime value; likelihood of engagement; propensity to unsubscribe; propensity to convert; propensity to buy; and propensity to churn.
Collaborative Filtering (Recommendations) – Used for recommending products, services, and advertisements to customers based on a variety of variables, including past buying behavior. Common models (like those used by Amazon and Netflix) include up-sell, cross-sell, and next-sell recommendations.
Regression analysis in its various forms is the primary tool that organizations use for predictive analytics. Defined in simple terms, an analyst performs a regression analysis to spot strength of correlations between specific customer variables with the purchase of a particular product; they can then use the “regression coefficients” (i.e. the degree to which each variable affects the purchase behavior) and create a score for likelihood of future purchases.
Outcomes for predictive modeling are, like so many predictive analytics approaches, highly dependent on proprietary data, but there are several common ways that this information can be transformed into results. For example, a brick-and-mortar marketing team might use all the information available on customers to make data-based decisions about which products and services are best to bring to market.
By using data visualization to shows which types of customers live in a store’s neighborhood, teams can hone in on important guiding questions: Do they buy more hard goods or soft? Is there an age-range density that shows what should be stocked? Does the desired product make-up change as you move towards or away from competitor locations?
This type of information can also be linked to overarching supply chain management strategies. Data visualization is a valuable tool that not only appeals to the eye, but can be used to inform, inspire and guide actions based on customer behavior (and other business information).
Targeting the right customers at the right moment with the best offer links back to customer segmentation. This may be the most common marketing application for predictive analytics because its one of the “simplest” and most direct ways to optimize a marketing offer and see a quick turnaround on better ROI.
According to a study by the Aberdeen Group, predictive analytics users are twice as likely to identify high-value customers and market the right offer. Your data set matters, and best practices dictate using historical data on behavior of existing customers to segment and target, and using that same data to create personalized messages.
A range of predictive analytic models can be used in this application, including affinity analysis, response modeling, and churn analysis, all of which can, for example, tell you whether it’s a good idea to combine digital and print subscriptions or keep them separate, or help you determine content that should be charged a subscription fee versus content that should be given a one-time sales price or other structure.
Many vendors, like Salesforce, are offering a marketing cloud platform, through which marketing teams can build audience profiles by combining data from multiple avenues, from CRM to offline data. Feeding the system appropriate data and tracking behavior over time builds a behavioral model that allows teams to make data-based decisions in real-time over the long term.
In addition to those outlined above, other drilled-down uses for predictive analytics in marketing include:
Predictive analytics insights yield an effective tool to cope with “channel proliferation and changing buyer behavior”; all of the applications above could be used to determine whether a marketing campaign through social media will have a greater impact, or whether one through mobile is more appropriate for the target audience.
Predictive analytics is one way to leverage all of that information, gain tangible new insights, and stay ahead of the competition.
This type of information can also be linked to overarching supply chain management strategies. Data visualization is a valuable tool that not only appeals to the eye, but can be used to inform, inspire and guide actions based on customer behavior (and other business information).
Targeting the right customers at the right moment with the best offer links back to customer segmentation. This may be the most common marketing application for predictive analytics because its one of the “simplest” and most direct ways to optimize a marketing offer and see a quick turnaround on better ROI.
According to a study by the Aberdeen Group, predictive analytics users are twice as likely to identify high-value customers and market the right offer. Your data set matters, and best practices dictate using historical data on behavior of existing customers to segment and target, and using that same data to create personalized messages.
A range of predictive analytic models can be used in this application, including affinity analysis, response modeling, and churn analysis, all of which can, for example, tell you whether it’s a good idea to combine digital and print subscriptions or keep them separate, or help you determine content that should be charged a subscription fee versus content that should be given a one-time sales price or other structure.
Many vendors, like Salesforce, are offering a marketing cloud platform, through which marketing teams can build audience profiles by combining data from multiple avenues, from CRM to offline data. Feeding the system appropriate data and tracking behavior over time builds a behavioral model that allows teams to make data-based decisions in real-time over the long term.
In addition to those outlined above, other drilled-down uses for predictive analytics in marketing include:
- Accessing internal structured data
- Accessing social media data
- Applying behavior scoring to customer data
Predictive analytics insights yield an effective tool to cope with “channel proliferation and changing buyer behavior”; all of the applications above could be used to determine whether a marketing campaign through social media will have a greater impact, or whether one through mobile is more appropriate for the target audience.
Predictive analytics is one way to leverage all of that information, gain tangible new insights, and stay ahead of the competition.
Predictive Analytics Is Everywhere
As the BI landscape evolves, predictive analytics is finding its way into more and more business use cases.
Retail: Follow an online customer in real-time to determine whether providing additional product information or incentives will increase the likelihood of a completed transaction.
Financial Services: Develop credit risk models. Forecast financial market trends. Predict the impact of new policies, laws and regulations on businesses and markets.
Manufacturing: Predict the location and rate of machine failures. Optimize raw material deliveries based on projected future demands.
Law Enforcement: Use crime trend data to define neighborhoods that may need additional protection at certain times of the year.
Online dating company eHarmony's Elevated Careers website and the handful of other vendors in the "predictive analytics for hiring" space. These platforms are still very much in their early days, but the idea of using data to predict which job seekers are the best fit for specifics jobs and companies has the potential to reinvent how human resources (HR) managers recruit talent.
Similarly, because nearly any business that exists today operates so many of it’s functions in digital space (finance, marketing, sales, customer relationships, vendor data, hiring, etc…), data is now aggregate-able and accessible in ways that it never way before.
Now even a small 2-person eCommerce operation with only $800,000 in annual revenues has more marketing data to manipulate and explore (organic search traffic, time-on-site, impressions, various PPC ad channels, customer lifetime value as tracked within a CRM, etc…) than a business many times it’s size just ten years ago.
Millennials entering marketing professionals know no other world than the world of digital, quantifiable metrics and data. This information allows companies of all sizes to train models and leverage predictive analytics.
The difference between conventional analytics and predictive analytics is simple and straightforward. Whereas traditional analytics generally focuses on insights impacting the here and now, predictive analytics aims to allow users to gaze into the near- and long-term future to pinpoint likely trends and upcoming behaviors.
The difference between conventional analytics and predictive analytics is simple and straightforward. Whereas traditional analytics generally focuses on insights impacting the here and now, predictive analytics aims to allow users to gaze into the near- and long-term future to pinpoint likely trends and upcoming behaviors.
Getting Started With Predictive Analytics
While getting started in predictive analytics isn't exactly a snap, it's a task that virtually any business can handle as long as one remains committed to the approach and is willing to invest the time and funds necessary to get the project moving. Beginning with a limited-scale pilot project in a critical business area is an excellent way to cap start-up costs while minimizing the time before financial rewards begin rolling in.
Once a model is put into action, it generally requires little upkeep as it continues to grind out actionable insights for many years. Virtually all predictive analytics adopters use tools provided by one or more external developers. Many such tools are tailored to meet the needs of specific enterprises and departments. Major predictive analytics software and service providers include:
Acxiom
IBM
Information Builders
Microsoft
SAP
SAS Institute
Tableau Software
Teradata
TIBCO Software
Acxiom
IBM
Information Builders
Microsoft
SAP
SAS Institute
Tableau Software
Teradata
TIBCO Software
