IT/Support & Operations

Analysis of IT support activities

The IT supervision teams of a large group had no consolidated vision of the support activity: thousands of unannotated tickets, heterogeneous formats between teams and no way to detect emerging trends. We built an unsupervised classification system that automatically identifies topics, their granularity, and dynamics.

Problem

IT supervision teams received thousands of support tickets in non-standardized formats (templates, chats, emails) without any usable annotation or categorization. It was impossible to know which subjects mobilized the most resources, which themes were growing and which were no longer current. Managers allocated their teams blindly, in response to the emergencies of the day, without the ability to anticipate. The need: a structured and automated vision of the support activity, at three levels of granularity, to move from reactive mode to proactive management.

Vue rapprochée d’une coupe transversale colorée d’une géode montrant des couches concentriques de minéraux en jaune, marron, rouge et vert.

Solution

What we built

We deployed 1 Data Scientist to design a comprehensive system for the automated analysis of IT support tickets.

Step 1 — Cleaning and standardization. Harmonization of ticket data from heterogeneous sources (templates, chats, emails) into a single usable format. Text cleaning and normalization to make data compatible with NLP algorithms.

Step 2 — Unsupervised ticket classification. Ticket clustering using unsupervised Machine Learning methods (LDA, DBSCAN, K-Means) to automatically identify request topics. The system produces three levels of precision, for example: Outlook → Certificate → Expiry, allowing you to zoom from macro to micro.

Step 3 — Trend detection. Temporal analysis of the topics identified to qualify each theme: emerging, constant or declining. Managers can see at a glance which problems are growing and which are resolving.

Step 4 — Report automation. The entire pipeline from ticket ingestion to the final report is automated. Managers receive up-to-date analysis without manual intervention.

Projects in the same category

See all projects

Supply Chain Optimization Application

A pharmaceutical distribution player had to rethink its entire supply chain: pharmacy assortment, inventory management and delivery channels. Operational research alone was no longer enough. We built the application that transformed its operations.

Social media trend detection

In a market where consumer behaviors change faster than decision cycles, a customer needed to anticipate trends instead of experiencing them. We built the platform that turns social media noise into actionable signals.

Yield of agricultural fields

The climate subsidiary of a French insurance leader needed to predict field yields across Germany to price a new drought insurance offer. Internal data was not enough. We built the predictive models that made the product marketable.

Customer needs analysis platform

A large French group needed to understand the current and future needs of its customers by aggregating a massive volume of consumer data. After a POC of 8 weeks, we industrialized a complete platform deployed on all French entities and is now being extended at the group level.

Skin scoring and analysis

A major player in luxury cosmetics had developed a skin scoring algorithm. Problem: no one could verify what the AI was based on to make its diagnosis. We built the visualization system that makes predictions transparent and deployable in stores and on mobile.

Beaconing detection

A large group's security team needed to identify beaconing signals, regular network traffic sent by potentially compromised machines to servers controlled by attackers. The volume of logs made manual detection impossible. We built the anomaly detection system capable of processing this data on a large scale.