Ecole d'ingénieur et centre de recherche en Sciences du numérique

Model monitoring and dynamic model selection in travel time-series forecasting

Candela, Rosa; Michiardi, Pietro; Filippone, Maurizio; Zuluaga, Maria A

ECML-PKDD 2020, The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 14-18 September 2020, Ghent, Belgium

Accurate travel products price forecasting is a highly desired feature that allows customers to take informed decisions about purchases, and companies to build and offer attractive tour packages. Thanks to machine learning (ML), it is now relatively cheap to develop highly accurate statistical models for price time-series forecasting. However, once models are deployed in production, it is their monitoring, maintenance and improvement which carry most of the costs and difficulties over time. We introduce a data-driven framework to continuously monitor and maintain deployed time-series forecasting models' performance, to guarantee stable performance of travel products price forecasting models. Under a supervised learning approach, we predict the errors of time-series forecasting models over time, and use this predicted performance measure to achieve both model monitoring and maintenance. We validate the proposed method on a dataset of 18K time-series from flight and hotel prices collected over two years and on two public benchmarks.    

Document Arxiv Bibtex

Titre:Model monitoring and dynamic model selection in travel time-series forecasting
Mots Clés:Model monitoring · Model maintenance · Time-series · Forecasting
Type:Conférence
Langue:English
Ville:Ghent
Pays:BELGIQUE
Date:
Département:Data Science
Eurecom ref:6211
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in ECML-PKDD 2020, The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 14-18 September 2020, Ghent, Belgium and is available at :
Bibtex: @inproceedings{EURECOM+6211, year = {2020}, title = {{M}odel monitoring and dynamic model selection in travel time-series forecasting}, author = {{C}andela, {R}osa and {M}ichiardi, {P}ietro and {F}ilippone, {M}aurizio and {Z}uluaga, {M}aria {A}}, booktitle = {{ECML}-{PKDD} 2020, {T}he {E}uropean {C}onference on {M}achine {L}earning and {P}rinciples and {P}ractice of {K}nowledge {D}iscovery in {D}atabases, 14-18 {S}eptember 2020, {G}hent, {B}elgium}, address = {{G}hent, {BELGIQUE}}, month = {09}, url = {http://www.eurecom.fr/publication/6211} }
Voir aussi: