Citation
L'auteur
Dataiku
- (Pas d'affiliation)
Copyright
Déclaration d'intérêts
Financements
Aperçu
Contenu
Compagny
PagesJaunes.fr is the French equivalent of the YellowPages. PagesJaunes.fr is the French
leader in local advertising and information on web, mobile, and print, with annual revenue of over $1Billion.
Challenge
Improve User Experience Without Increasing Workload
More than 80% of the French rely on PagesJaunes.fr to get information or promote
their activity, generating hundreds of millions of queries each year. The quality and
relevance of results is a top priority for PagesJaunes. Category managers are
responsible for maintaining the quality and relevance of the directory by creating the
pertinent associations between terms and categories.
PagesJaunes wanted a solution that would help them:
- Measure and improve customer satisfaction,
- Help Category Managers automatically detect and correct problematic queries,
- Optimize the quality of results to improve customer satisfaction.
Solution
Score Customer Satisfaction & Automate Detection of False
Queries
With Dataiku Data Science Studio (DSS), PagesJaunes built an app that scores customer
satisfaction. First, the app gathers search engine data (query lists, navigation logs,
clicks, page visit rankings, etc.) and analyses them in order to isolate unsuccessful
queries.
Thanks to the creation of an algorithm, a score is computed for every query and is then
used to predict which queries will provide unsatisfactory results for users. The
algorithm is fed with qualified and enriched usage data.
The technology eventually targets the engine’s failures enabling category managers to
focus their operations on those failures.
Results
30% Boost in Category Manager Productivity & Optimized Customer Experience
PagesJaunes now has the capacity to explore and correlate heterogeneous and multiple data sources to deduce rules and models that can create value and be fed back into the app. PagesJaunes is constantly able to improve customer satisfaction all the while improving Category Manager’s productivity by:
- Closely monitoring and managing unsuccessful searches,
- Automatically detecting the most critical signals & applying the most relevant rules
when interpreting a query, - Targeting and fixing false query results.
“With DSS, we built an app in only 3 months that enabled a 30% boost in our
team’s productivity. We were able to adopt Hadoop and Machine Learning faster
than we had anticipated.” Erwan Pigneul, Project Manager – PagesJaunes
Since the project started, more than ten PagesJaunes’ collaborators have been trained
to Big Data technologies (Hadoop, machine learning, statistics) with DSS.
il ne peut pas avoir d'altmétriques.)