ML2Grow

Case

The Belgian Data Protection Authority (Belgian DPA) is responsible for compliance with the data protection regulations in Belgium. Every day, it deals with high volumes of questions from the public about data protection. It has prepared answers to frequently asked questions and interpretations and clarifications on the law. However, specialists at the Belgian DPA spend a lot of time answering similar questions that have already been discussed in the past.

The problem

The Belgian Data Protection Authority receives questions requests from citizens and organisations via email. These questions need to be linked by an expert to certain ruling and legislation, after which an answer is presented and published on the website. 

Many of the incoming requests have already been published, and in these cases, the expert spends time simply linking the previous publication(s) to the incoming request.

The Belgian Data Protection authority wanted to explore the possibility of using an intelligent agent integrated into a website, which could automate this. The agent would need to start a natural conversation and, in an intelligent way, guide the conversation to the relevant publications and documents.

Our solution

We used machine learning to solve this problem. Firstly, we modelled the topic. This meant we could identify the relevant theme in the data protection legislation. We used this information to steer the questioning and conversation. Secondly, we created an intelligent agent. This was used to mine information and steer the conversation, functioning in several languages. If the interaction with the user did not resolve the question, the intelligent agent presented the user with a search function to retrieve relevant publications.

Work performed

• Examining the underlying structure of document collections
• Intelligent agent
• High-precision search engine

How we added value

• We provided a more efficient and natural way to inform citizens and organisations properly.

Work performed

• Predictive machine learning models that capture planning uncertainties

Added value

• Captures the planning horizon for up to 8 hours
• Avoid expensive capacity shortages
• Reliable simulations of personnel assignments and alternative scenarios

The port of Antwerp is a world in itself. Very few outsiders know what really happens in Europe’s second largest port. Everyone knows the classic image of ships coming and going to load and unload goods. To make this possible, numerous players are needed, each of whom forms an indispensable link in the nautical chain in the port area: from lockmen, bridge keepers, tug crews and ship coordinators to pilots and boatmen. The safe piloting, mooring and unmooring of ships is the core business of Brabo.

Brabo provides training for port pilots and pilot services for the control of incoming and outgoing ships in the port of Antwerp. In order to be able to cope with the increasing demand and always have sufficient capacity without unnecessary (high wage) costs, Brabo decided to invest in technology that predicts demand, enables better planning and avoids a capacity shortage in view of the associated high (private and social) costs. ML2Grow was able to offer them this technology.

Answering these questions was no easy task, the pilotage time of ships must be predicted on the basis of a large complexity of parameters: type of ship, size of the ship, draft, place of departure and destination, equipment (stern thruster, bow thruster), tugs, …

ML2Grow was able to successfully make a predictive machine learning system operational, enabling the port to react more quickly with their ship operations. Thanks to these models, Brabo’s pilot service window could be improved from 20 minutes to 8 hours, making a huge difference in Europe’s second-largest port.

This was a textbook example of the kind of problem ML2Grow is eager to solve: applying advanced machine learning to business challenges within a global context.

The rapid emergence of artificial intelligence offers unseen possibilities to build new applications that add clear and immediate value to organizations. Building on solid academic foundations and driven by strong ambitions to impact the world, ML2Grow is operating at the core of this ongoing evolution.

Case

Annabel Textiles is a family business established in 1970 and has since become an international player in the high-quality fabrics market. It designs and weaves fabrics for the Belgian market and exports its products worldwide. It also imports fabrics from Asia, which it distributes and finishes.

The problem

Due to a large number of designs in its collection, the company was spending excessive amounts of time on manual quality inspections to compare fabrics with standard samples. As its designs and samples were always changing, the company had difficulty providing its sales team with the latest designs in the range. The company also needed a simple way of presenting its fabrics to customers instead of carrying around a heavy case with every single sample.

Our solution

We installed a camera to take high-resolution images of each sample that we used in a digital catalogue. We created an AI model to accurately label fabrics according to their properties, such as their colour and pattern. Now the samples no longer need to be checked manually. The company can now automatically compare fabrics against standard samples using an AI model, which increases the efficiency of operators.

How we added value

• Greater speed and efficiency – operators can work more quickly and automatically detect weaving flaws.
• Fewer returned products – the fabrics are checked more thoroughly for defects.
• Improved operator job satisfaction - by fully or partially automating repetitive tasks