Details

Athennian is a growing tech start-up which has a cloud platform for legal entity management. We would like to collaborate with students to strategically apply AI and machine learning methodologies to data migration. This is a great learning opportunity to solve a real-world problem and will allow our company to onboard new customers more efficiently.

Athennian receives unstructured data related to various legal entities from different customer sources. This data needs to be extracted and converted into a structured csv format for compatibility with our in-house software.

Students should be prepared to:

• Apply machine learning methodologies to identify relevant data from various PDF and Word documents.
• Automate the process for extracting relevant data and mapping it into a structured data format.
• Design processes and test cases to ensure improvement in the accuracy of the tool over time.

Athennian has over 250 variables that may be identified for extraction, of various data types including names, dates, addresses, numbers, and string text. There is meta-data for the documents that can impact the ability to detect the structure of the data, including the type of document being interpreted and the legal entity type the document belongs to.