Automatic ordering of amendments from presentation order to voting order

Use case ID: 004

Author: IT Department, Chamber of Deputies of Italy

Date: 22 May 2024

Objective: 

Amendments are received, stored and numbered according to presentation time. Business units need to have amendments ordered according to voting order.

Actors: 

• Business units
• Dossier of amendments 

Prerequisites:

• Amendments stored in a structured way inside a database
• Dossier of amendments stored in a content management system
• Knowledge of the rules according to which amendments are to be ordered according to voting order

Scenario:

1. The amendments are submitted by MPs, received by offices, stored in a structured way inside a database and numbered according to presentation time.
2. The dossier of amendments is produced and stored in a structured way (i.e. JSON format).
3. The ordering algorithm, based on pattern matching and AI, is executed on the dossier of amendments; it produces, as output, a new JSON file representing the dossier of amendments ordered according to voting order.
4. It may be convenient for business units to have a drag-and-drop window for minor modifications to the ordering.
5. The business units keep working on the dossier of amendments (legislative drafting and inadmissibility speeches).

Expected results:

• It takes less time to order the dossier of amendments according to voting order.

Potential challenges:

• Strong collaboration is needed between the IT Department and business units in order to have clear documentation regarding ordering rules.
• It may be necessary to periodically retrain the model, so the potential use of MLOps should be evaluated.
• The ordering produced might not be 100% accurate, so it may be convenient for business units to have a drag-and-drop window for minor modifications that may be needed on the dossier.

Data requirements:

• Structured representation of the dossier of amendments (i.e. JSON format)
• Amendment texts and metadata stored inside a database

Integrations with other systems:

• Database containing amendments texts and metadata
• Software application used for legislative drafting and for other procedural tasks on amendments

Success metrics:

• Time needed to order the dossier
• The difference between the time needed to automatically order the dossier and the time that would have been needed for the ordering without using the algorithm
• The percentage of amendments manually moved using the drag-and-drop window after the execution of the ordering algorithm
• Colleague satisfaction scores