Model Monitoring and Dynamic Model Selection in Travel Time-Series Forecasting View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2021-02-25

AUTHORS

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

ABSTRACT

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. More... »

PAGES

513-529

Book

TITLE

Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track

ISBN

978-3-030-67666-7
978-3-030-67667-4

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-030-67667-4_31

DOI

http://dx.doi.org/10.1007/978-3-030-67667-4_31

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1135710800


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/14", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Economics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1403", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Econometrics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Data Science Department, EURECOM, Biot, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "Data Science Department, EURECOM, Biot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Candela", 
        "givenName": "Rosa", 
        "id": "sg:person.012523360247.17", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012523360247.17"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Data Science Department, EURECOM, Biot, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "Data Science Department, EURECOM, Biot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Michiardi", 
        "givenName": "Pietro", 
        "id": "sg:person.016057235273.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016057235273.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Data Science Department, EURECOM, Biot, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "Data Science Department, EURECOM, Biot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Filippone", 
        "givenName": "Maurizio", 
        "id": "sg:person.07706215665.03", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07706215665.03"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Amadeus SAS, Sophia Antipolis, France", 
          "id": "http://www.grid.ac/institutes/None", 
          "name": [
            "Data Science Department, EURECOM, Biot, France", 
            "Amadeus SAS, Sophia Antipolis, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Zuluaga", 
        "givenName": "Maria A.", 
        "id": "sg:person.01020775531.36", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01020775531.36"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2021-02-25", 
    "datePublishedReg": "2021-02-25", 
    "description": "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\u2019 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.", 
    "editor": [
      {
        "familyName": "Dong", 
        "givenName": "Yuxiao", 
        "type": "Person"
      }, 
      {
        "familyName": "Mladeni\u0107", 
        "givenName": "Dunja", 
        "type": "Person"
      }, 
      {
        "familyName": "Saunders", 
        "givenName": "Craig", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-030-67667-4_31", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-030-67666-7", 
        "978-3-030-67667-4"
      ], 
      "name": "Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track", 
      "type": "Book"
    }, 
    "keywords": [
      "time series forecasting model", 
      "time series forecasting", 
      "forecasting model", 
      "price forecasting model", 
      "dynamic model selection", 
      "price forecasting", 
      "hotel prices", 
      "model monitoring", 
      "forecasting", 
      "tour packages", 
      "accurate statistical models", 
      "performance measures", 
      "model selection", 
      "prices", 
      "statistical model", 
      "purchase", 
      "informed decisions", 
      "companies", 
      "model", 
      "decisions", 
      "cost", 
      "data-driven framework", 
      "customers", 
      "benchmarks", 
      "framework", 
      "measures", 
      "machine learning", 
      "dataset", 
      "performance", 
      "package", 
      "approach", 
      "production", 
      "time", 
      "years", 
      "difficulties", 
      "selection", 
      "thanks", 
      "improvement", 
      "error", 
      "flight", 
      "supervised learning approach", 
      "learning approach", 
      "public benchmarks", 
      "features", 
      "method", 
      "learning", 
      "maintenance", 
      "monitoring", 
      "stable performance", 
      "Accurate travel products price forecasting", 
      "travel products price forecasting", 
      "products price forecasting", 
      "attractive tour packages", 
      "price time-series forecasting", 
      "deployed time-series forecasting models", 
      "travel products price forecasting models", 
      "products price forecasting models", 
      "Travel Time-Series Forecasting"
    ], 
    "name": "Model Monitoring and Dynamic Model Selection in Travel Time-Series Forecasting", 
    "pagination": "513-529", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1135710800"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-030-67667-4_31"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-030-67667-4_31", 
      "https://app.dimensions.ai/details/publication/pub.1135710800"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:14", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_241.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-030-67667-4_31"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-67667-4_31'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-67667-4_31'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-67667-4_31'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-67667-4_31'


 

This table displays all metadata directly associated to this object as RDF triples.

161 TRIPLES      23 PREDICATES      85 URIs      76 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-030-67667-4_31 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 anzsrc-for:14
4 anzsrc-for:1403
5 schema:author N15c61b08306740f2bd57199a6162225a
6 schema:datePublished 2021-02-25
7 schema:datePublishedReg 2021-02-25
8 schema:description 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.
9 schema:editor N878452846fb746b0822ac265b8b4785c
10 schema:genre chapter
11 schema:inLanguage en
12 schema:isAccessibleForFree true
13 schema:isPartOf Nfb20cec0adcd4619aa603f9f09c6e812
14 schema:keywords Accurate travel products price forecasting
15 Travel Time-Series Forecasting
16 accurate statistical models
17 approach
18 attractive tour packages
19 benchmarks
20 companies
21 cost
22 customers
23 data-driven framework
24 dataset
25 decisions
26 deployed time-series forecasting models
27 difficulties
28 dynamic model selection
29 error
30 features
31 flight
32 forecasting
33 forecasting model
34 framework
35 hotel prices
36 improvement
37 informed decisions
38 learning
39 learning approach
40 machine learning
41 maintenance
42 measures
43 method
44 model
45 model monitoring
46 model selection
47 monitoring
48 package
49 performance
50 performance measures
51 price forecasting
52 price forecasting model
53 price time-series forecasting
54 prices
55 production
56 products price forecasting
57 products price forecasting models
58 public benchmarks
59 purchase
60 selection
61 stable performance
62 statistical model
63 supervised learning approach
64 thanks
65 time
66 time series forecasting
67 time series forecasting model
68 tour packages
69 travel products price forecasting
70 travel products price forecasting models
71 years
72 schema:name Model Monitoring and Dynamic Model Selection in Travel Time-Series Forecasting
73 schema:pagination 513-529
74 schema:productId N8c23e83694784073a60c6afb5fb806fc
75 Nace6095e5874431c990d90ac718d2810
76 schema:publisher Nb17a539b9e264f90bd429c4b76a25d1d
77 schema:sameAs https://app.dimensions.ai/details/publication/pub.1135710800
78 https://doi.org/10.1007/978-3-030-67667-4_31
79 schema:sdDatePublished 2022-01-01T19:14
80 schema:sdLicense https://scigraph.springernature.com/explorer/license/
81 schema:sdPublisher N4662bdc46324470c9319aa79d5cf0262
82 schema:url https://doi.org/10.1007/978-3-030-67667-4_31
83 sgo:license sg:explorer/license/
84 sgo:sdDataset chapters
85 rdf:type schema:Chapter
86 N15c61b08306740f2bd57199a6162225a rdf:first sg:person.012523360247.17
87 rdf:rest Nc5724a268f104c4b967a21206759b8b2
88 N352506f62d1e497bb0ab6bc89dff5e37 rdf:first N6ff25b274ff349e097e70b3eee575a52
89 rdf:rest N64be96ab422d43df9da0efa1acdb1354
90 N4662bdc46324470c9319aa79d5cf0262 schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 N64be96ab422d43df9da0efa1acdb1354 rdf:first N69e2d8c871cf4249a818649808ade055
93 rdf:rest rdf:nil
94 N69e2d8c871cf4249a818649808ade055 schema:familyName Saunders
95 schema:givenName Craig
96 rdf:type schema:Person
97 N6ff25b274ff349e097e70b3eee575a52 schema:familyName Mladenić
98 schema:givenName Dunja
99 rdf:type schema:Person
100 N75a69b80e43c4f49b27abf7fc3130ec8 rdf:first sg:person.07706215665.03
101 rdf:rest Na23b1906462e45009f0ae702d516fd57
102 N878452846fb746b0822ac265b8b4785c rdf:first Nb96cfdb1da894743ab3818b58b453c9a
103 rdf:rest N352506f62d1e497bb0ab6bc89dff5e37
104 N8c23e83694784073a60c6afb5fb806fc schema:name dimensions_id
105 schema:value pub.1135710800
106 rdf:type schema:PropertyValue
107 Na23b1906462e45009f0ae702d516fd57 rdf:first sg:person.01020775531.36
108 rdf:rest rdf:nil
109 Nace6095e5874431c990d90ac718d2810 schema:name doi
110 schema:value 10.1007/978-3-030-67667-4_31
111 rdf:type schema:PropertyValue
112 Nb17a539b9e264f90bd429c4b76a25d1d schema:name Springer Nature
113 rdf:type schema:Organisation
114 Nb96cfdb1da894743ab3818b58b453c9a schema:familyName Dong
115 schema:givenName Yuxiao
116 rdf:type schema:Person
117 Nc5724a268f104c4b967a21206759b8b2 rdf:first sg:person.016057235273.37
118 rdf:rest N75a69b80e43c4f49b27abf7fc3130ec8
119 Nfb20cec0adcd4619aa603f9f09c6e812 schema:isbn 978-3-030-67666-7
120 978-3-030-67667-4
121 schema:name Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track
122 rdf:type schema:Book
123 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
124 schema:name Mathematical Sciences
125 rdf:type schema:DefinedTerm
126 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
127 schema:name Statistics
128 rdf:type schema:DefinedTerm
129 anzsrc-for:14 schema:inDefinedTermSet anzsrc-for:
130 schema:name Economics
131 rdf:type schema:DefinedTerm
132 anzsrc-for:1403 schema:inDefinedTermSet anzsrc-for:
133 schema:name Econometrics
134 rdf:type schema:DefinedTerm
135 sg:person.01020775531.36 schema:affiliation grid-institutes:None
136 schema:familyName Zuluaga
137 schema:givenName Maria A.
138 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01020775531.36
139 rdf:type schema:Person
140 sg:person.012523360247.17 schema:affiliation grid-institutes:grid.28848.3e
141 schema:familyName Candela
142 schema:givenName Rosa
143 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012523360247.17
144 rdf:type schema:Person
145 sg:person.016057235273.37 schema:affiliation grid-institutes:grid.28848.3e
146 schema:familyName Michiardi
147 schema:givenName Pietro
148 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016057235273.37
149 rdf:type schema:Person
150 sg:person.07706215665.03 schema:affiliation grid-institutes:grid.28848.3e
151 schema:familyName Filippone
152 schema:givenName Maurizio
153 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07706215665.03
154 rdf:type schema:Person
155 grid-institutes:None schema:alternateName Amadeus SAS, Sophia Antipolis, France
156 schema:name Amadeus SAS, Sophia Antipolis, France
157 Data Science Department, EURECOM, Biot, France
158 rdf:type schema:Organization
159 grid-institutes:grid.28848.3e schema:alternateName Data Science Department, EURECOM, Biot, France
160 schema:name Data Science Department, EURECOM, Biot, France
161 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...