It is time to improve data-driven decision making in schools

Since the launch of National Education Management Information System (NEMIS) a web based data-driven solution in Kenyan schools in 2017, the dream of automating data and related administrative functions have steadily been on the rise but more need to be done to achieve real-time analysis says Timothy Oriedo, the Founder CEO of Predictive Analytics.

From the outset, the main objective of NEMIS portal was to help the Ministry of Education to gather accurate and real-time information on learners and learning institutions states Oriedo who is also the author of Big Data and Predictive Analytics: Raise your Data Quotient.

According to Oriedo, an effective Education Management Information System not only gathers statistics from the schools by following people, models, methods, procedures, processes, rules and regulations but also relates with the emerging computer technology to get all mentioned functions work together. “NEMIS in this regard should provide comprehensive, integrated, relevant, reliable, unambiguous and timely data to the educators, decision- makers and sector planners,” Oriedo asserted.

“NEMIS in this regard should provide comprehensive, integrated, relevant, reliable, unambiguous and timely data to the educators, decision- makers and sector planners,”

Timothy Oriedo., Founder Predictive Analytics.

However, since its inception, the system, as is typical to any new technological intervention that is deployed enmasse, has had its fair share of bottlenecks ranging from data incompleteness, technical incapacity of users to lack of synchronization with data on the Integrated Population Regulations Systems (IPRS) says Oriedo.

“IPRS was intended to store data of all Kenyans at a central location for easy electronic access by institutions, including private corporations that provide crucial and sensitive services,” was intended to store data.

Despite this challenges, the gains made have been immense and these year Ministry went a notch higher by activating a module for Form one admissions into secondary schools. The Ministry of Education released a guide to form one admission for schools using the NEMIS to guide school principals on admission criteria. However, there was a backlash for a variety of reasons and this offers valuable lessons to pick from as Kenya drives toward adopting the culture of data driven decisions in both public and private corporations.

Lesson # 1 Digital Transformation is driven by consumer education.

The Ministry directed that all admission letters for 3 categories of schools, apart from Sub County schools, must be downloaded from the NEMIS website.

The deliberate move, though positive posed a challenge bearing in mind the remote location of the parents and their level of digital literacy says Oriedo adding: “It will be worthy for the ministry to look at data from the portal and ascertain how many parents actually downloaded as directed. There is a need to provide education through mass media to the parents on how to go about downloading the forms prior to enforcement of the directive.”

Lesson # 2 Behavioral Metadata

What story does the data speak? Oriedo notes that it is critical to review the previous data in the Ministry and what has been the trend of admission. Do students report to the schools that they have been selected? For those who don’t, how do they settle on the school they eventually report? For the schools that have a substantial number of no shows, how do they fill the void? Who is the key decision maker in selection, is it the student or the parent? Why is it that many parents prefer to take their kids to students of their choice? Who then should the selection exercise target?

Lesson # 3 Algorithmic Vs Humagorithmic Selection

The Ministry states that the selection process is computer generated. Well, but the data is input by humans and the algorithms are tuned by humans too. To what extend does the human and algorithms work together?  What optimized is the selection algorithm to avoid True Positives and False Negatives or such instances where one is posted to a school they didn’t select. Does the selection criteria match the parents preferences? How involved are parents during the selection criteria? Can the enforcement happen at this stage that is usually at the beginning of the Class 8 term where the consequences of selection are clearly stated to manage anticipations.

Lesson # 4 Location Intelligence

How well does the NEMIS system make use of geographical information mapping. In the spirit of regional balance and cultural adaptation as a criteria, it would be worthwhile to analyze longitudinal impact of education performance of learners from different environment for future placement considerations.  There are reported instances of pupils were selected to join day county day schools or mixed schools far away from student residence. Which in practicality forces a parent to rent a house for the student.

Lesson # 5 Technology enables Strategy

The availability of Data does not necessarily mean the data will speak for itself. Despite the good work done so far in setting up an efficient system in collecting the data, its time the ministry raises the bar by investing in the right technology to scale the usage of the platform for multiple access recommends Oriedo.

“There is need to as well invest in technologies supporting data collection, processing, and analytics besides hiring skilled consultants who will guide in integrating the data with machine learning models that will enable near-real-time prediction use cases that influence operational decision making asserted Oriedo.

Computer technology provides technical support to the education management information systems by providing right people with right information at the right time to make best decisions, planning and monitoring in the best interest of organization.

Incidentally, by time of writing this article, NEMIS website was down probably because it couldn’t handle the massive volume of interactions by multiple users.