Sorry, you need to enable JavaScript to visit this website.
Predictive Analytics

Predictive Analytics

What is Predictive Analytics?

Predictive analytics describe what’s likely to happen in the future. It uses techniques like data mining, statistics, modelling, machine learning, and artificial intelligence to exploit patterns found in historical and current data to make predictions about the likelihood of future events, hence identify potential opportunities and risks before they occur.


What are the common predictive analytics applications?

Student learning: predictive analytics can help determine potential factors that lead to academic success or failure, hence identify students at risk and offer assistance at an early stage.

Fundraising: a model can be built to identify high potential donors through analyzing the client database, past donors’ information etc., hence while reducing the cost of donor acquisition, increasing the chances of getting donations.


What are the benefits of applying predictive analytics?

  • Retailers can use predictive analytics to gain insights into the success of new products. Utility operators can use predictive analytics to reduce the risk of downtime.   Predictive Analytics help reduce operational risk.
  • Lower risk used to translate into lower cost. The better you can predict the future, the more measures you can take to minimize potential higher adverse financial impacts.
  • Predictive analytics can help business to identify the product / service with a higher success rate.  Resources could then be allocated to those areas to boost productivity & operational efficiency.
  • The more data you collect, the more accurate your analytics will become.  Predictive analytics uses AI algorithms to almost instantly process bulk volume of data and provide insights in a much more effective way, compared to traditional statistical algorithms and human analysis. 


Where do we use predictive analytics in HKUST?

Since 2018, HKUST has started experimental projects applying Predictive Analytics.  ISO has partnered with various department / office, engaged expert consultants to help us build various Proof of Concept models in predicting student performance (SSCI/MATH, LANG), faulty of a higher chance of securing a grant (RO), potential alumni in donating to the University (DAO).   

A predictive model for predicting the likely donors based on different segments has been developed for DAO.