EDUCE

Problem

• Every university has its own transcript formats

• Transcript data coming from diverse systems and software is not standardized

• Quality of received documents varies including poorly done scans

• Transcripts often include superfluous information, not directly releated to student performance

• Significant manual effort in extracting and mapping data

• The extraction process can be error-prone

• Read and interpret system generated and scanned transcript PDFs intelligently

• Extract the data, export it in machine readable formats such as JSON, XML, and XLS

• It can be mapped to standard nomenclature and grading pattern

• It can be imported into MIS software or student system

• Will allow evaluators to complete evaluations quickly

• Will allow universities to run advanced analytics in aid of better decision-making

• Save substantially on current manual work

A step towards the holy grail of machine-readable data-exchange between entities