Please ensure Javascript is enabled for purposes of website accessibility Predictive Analytics and Modeling (PAM) Lab | University of West Florida
Skip to main content

Predictive Analytics and Modeling (PAM) Lab

charts and graphs

The PAM lab specializes in developing easy-to-understand analytics for decision-making and data predictions.


The Predictive Analytics and Modeling (PAM) Lab is at the forefront of transforming data into actionable insights. Our flagship product, a student success dashboard, is revolutionizing the education sector by enabling universities to harness the power of their data. Seamlessly integrate your data from various sources, including demographics, course performance, and advising notes, and provide a comprehensive view of your institution's health. 

Our dashboard leverages advanced predictive modeling and data visualization techniques to personalize student and institutional success. University administrators can now access the information they need to make informed decisions, track the impact of new initiatives, and explore innovative strategies to support student success. 

The PAM Lab also offers customized data services to businesses and organizations across various sectors. We help our clients make data-informed decisions, streamline their operations, and gain a competitive edge in their respective markets. 

The PAM Lab is your trusted partner in driving meaningful change in your organization and reaching the full potential your data can provide. Contact Lesley Cox at lcox3@uwf.edu to learn more about our student success dashboard and discover how our data solutions can help you achieve your goals.

 

Statistical and Analytical Services

The PAM Lab offers its statistical and analytical services to both internal and external clients. Depending on the scope of the project, the PAM Lab offers varying fee schedules.

Data Analytics Service Fees

Depending on the organization’s needs, and the amount and type of data being collected; the PAM Lab has the expertise to build the following types of analytics for an organization to help improve business processes and decision-making efforts (included are examples for each type of analytics):

To assist organizations in comprehending their data and providing insights into historical trends. The purpose is to summarize, describe, and understand data patterns, trends, and distributions.

  1. Build customer profiles.
    (Who is the typical customer for this item/service?).
  2. Synthesize item profiles.
    (When does this item/service sell? What goods are associated with this item? Does demand fluctuate?)
  3. Find groups of customers and items based on similarity, and the associations between the customer groups and items
    (sporadic single item customers, weekend shopper, etc.).

To determine changes in sales trends, customer behavior, or product performance. The purpose is to find connections and irregularities in data and understand the underlying causes of behavior.

  1. Track customer retention.
  2. Measure the effect of business campaigns.
  3. Discover items with increased or decreased demand.

To predict future events or outcomes regarding product performance, customer behavior, or employee behavior. The purpose is to help organizations make proactive decisions and to provide insights into potential risks and opportunities.

  1. Identify customers likely to churn (at-risk).
  2. Target changing item demand for business campaigns.
  3. Analyze external trends to forecast future business.

To provide recommendations and suggestions for action based on predictions made.

  1. List at-risk customers for communication or promotions.
  2. Recommend good-fit items to customers.
  3. Automate frequent business processes.

To process and analyze vast amounts of unstructured data to make contextual inferences and determine analytic-driven information.

  1. Provide search functionality for unstructured data. (Find documents (data) containing a keyword or similar phrase).
  2. Monitor customer interactions.
  3. Extract themes and sentiments from customer reviews.

Summary

Data analytics can be broken into four key types:

  • Descriptive, which answers the question, “What happened?”
  • Diagnostic, which answers the question, “Why did this happen?”
  • Predictive, which answers the question, “What might happen in the future?”
  • Prescriptive, which answers the question, “What should we do next?”