Learning ‘Good Quality’ Resource Allocations from Historical Data View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015-09-02

AUTHORS

Renuka Sindhgatta , Aditya Ghose , Gaargi Banerjee Dasgupta

ABSTRACT

Effective and efficient delivery of services requires tasks to be allocated to appropriate and available set of resources. Much of the research in task allocation, model a system of tasks and resources and determine which tasks should be executed by which resources. These techniques when applied to service systems with human resources, model parameters that can be explicitly identified, such as worker efficiency, worker capability based on skills and expertise, authority derived from organizational positions and so on. However, in real-life workers have complex behaviors with varying efficiencies that are either unknown or are increasingly complex to model. Hence, resource allocation models that equate human performance to device or machine performance could provide inaccurate results. In this paper we use data from process execution logs to identify resource allocations that have resulted in an expected service quality, to guide future resource allocations. We evaluate data for a service system with 40 human workers for a period of 8 months. We build a learning model using Support Vector Machine (SVM), that predicts the quality of service for specific allocation of tasks to workers. The SVM based classifier is able to predict service quality with 80 % accuracy. Further, a latent discriminant classifier, uses the number of tasks pending in a worker’s queue as a key predictor, to predict the likelihood of allocating a new incoming request to the worker. A simulation model that incorporates the dispatching policy based on worker’s pending tasks shows an improved service quality and utilization of service workers. More... »

PAGES

84-95

Book

TITLE

Service-Oriented Computing - ICSOC 2014 Workshops

ISBN

978-3-319-22884-6
978-3-319-22885-3

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-22885-3_8

DOI

http://dx.doi.org/10.1007/978-3-319-22885-3_8

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1003147418


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Wollongong, Wollongong, NSW, Australia", 
          "id": "http://www.grid.ac/institutes/grid.1007.6", 
          "name": [
            "IBM Research-India, Bangalore, India", 
            "University of Wollongong, Wollongong, NSW, Australia"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Sindhgatta", 
        "givenName": "Renuka", 
        "id": "sg:person.015651720511.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015651720511.55"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "University of Wollongong, Wollongong, NSW, Australia", 
          "id": "http://www.grid.ac/institutes/grid.1007.6", 
          "name": [
            "University of Wollongong, Wollongong, NSW, Australia"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ghose", 
        "givenName": "Aditya", 
        "id": "sg:person.015573517335.70", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015573517335.70"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "IBM Research-India, Bangalore, India", 
          "id": "http://www.grid.ac/institutes/grid.481550.d", 
          "name": [
            "IBM Research-India, Bangalore, India"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dasgupta", 
        "givenName": "Gaargi Banerjee", 
        "id": "sg:person.011623557301.33", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011623557301.33"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2015-09-02", 
    "datePublishedReg": "2015-09-02", 
    "description": "Effective and efficient delivery of services requires tasks to be allocated to appropriate and available set of resources. Much of the research in task allocation, model a system of tasks and resources and determine which tasks should be executed by which resources. These techniques when applied to service systems with human resources, model parameters that can be explicitly identified, such as worker efficiency, worker capability based on skills and expertise, authority derived from organizational positions and so on. However, in real-life workers have complex behaviors with varying efficiencies that are either unknown or are increasingly complex to model. Hence, resource allocation models that equate human performance to device or machine performance could provide inaccurate results. In this paper we use data from process execution logs to identify resource allocations that have resulted in an expected service quality, to guide future resource allocations. We evaluate data for a service system with 40 human workers for a period of 8\u00a0months. We build a learning model using Support Vector Machine (SVM), that predicts the quality of service for specific allocation of tasks to workers. The SVM based classifier is able to predict service quality with 80\u00a0% accuracy. Further, a latent discriminant classifier, uses the number of tasks pending in a worker\u2019s queue as a key predictor, to predict the likelihood of allocating a new incoming request to the worker. A simulation model that incorporates the dispatching policy based on worker\u2019s pending tasks shows an improved service quality and utilization of service workers.", 
    "editor": [
      {
        "familyName": "Toumani", 
        "givenName": "Farouk", 
        "type": "Person"
      }, 
      {
        "familyName": "Pernici", 
        "givenName": "Barbara", 
        "type": "Person"
      }, 
      {
        "familyName": "Grigori", 
        "givenName": "Daniela", 
        "type": "Person"
      }, 
      {
        "familyName": "Benslimane", 
        "givenName": "Djamal", 
        "type": "Person"
      }, 
      {
        "familyName": "Mendling", 
        "givenName": "Jan", 
        "type": "Person"
      }, 
      {
        "familyName": "Ben Hadj-Alouane", 
        "givenName": "Nejib", 
        "type": "Person"
      }, 
      {
        "familyName": "Blake", 
        "givenName": "Brian", 
        "type": "Person"
      }, 
      {
        "familyName": "Perrin", 
        "givenName": "Olivier", 
        "type": "Person"
      }, 
      {
        "familyName": "Saleh Moustafa", 
        "givenName": "Iman", 
        "type": "Person"
      }, 
      {
        "familyName": "Bhiri", 
        "givenName": "Sami", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-22885-3_8", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-22884-6", 
        "978-3-319-22885-3"
      ], 
      "name": "Service-Oriented Computing - ICSOC 2014 Workshops", 
      "type": "Book"
    }, 
    "keywords": [
      "support vector machine", 
      "resource allocation", 
      "process execution logs", 
      "service system", 
      "service quality", 
      "quality of service", 
      "new incoming requests", 
      "number of tasks", 
      "execution logs", 
      "resource allocation model", 
      "task allocation", 
      "incoming requests", 
      "human workers", 
      "vector machine", 
      "learning model", 
      "improved service quality", 
      "discriminant classifier", 
      "system of tasks", 
      "task", 
      "classifier", 
      "human performance", 
      "allocation model", 
      "historical data", 
      "available set", 
      "allocation", 
      "future resource allocation", 
      "simulation model", 
      "services", 
      "resources", 
      "worker efficiency", 
      "queue", 
      "inaccurate results", 
      "machine performance", 
      "good quality", 
      "machine", 
      "system", 
      "requests", 
      "complex behavior", 
      "performance", 
      "worker capabilities", 
      "human resources", 
      "model parameters", 
      "quality", 
      "model", 
      "accuracy", 
      "capability", 
      "specific allocation", 
      "efficiency", 
      "data", 
      "set", 
      "logs", 
      "efficient delivery", 
      "organizational position", 
      "devices", 
      "expertise", 
      "technique", 
      "utilization", 
      "research", 
      "number", 
      "determine", 
      "results", 
      "skills", 
      "position", 
      "policy", 
      "parameters", 
      "authorities", 
      "delivery", 
      "workers", 
      "behavior", 
      "key predictors", 
      "likelihood", 
      "service workers", 
      "predictors", 
      "period", 
      "months", 
      "paper"
    ], 
    "name": "Learning \u2018Good Quality\u2019 Resource Allocations from Historical Data", 
    "pagination": "84-95", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1003147418"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-22885-3_8"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-22885-3_8", 
      "https://app.dimensions.ai/details/publication/pub.1003147418"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:49", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_259.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-22885-3_8"
  }
]
 

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.10.1007/978-3-319-22885-3_8'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-22885-3_8'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-22885-3_8'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-22885-3_8'


 

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

198 TRIPLES      22 PREDICATES      100 URIs      93 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-22885-3_8 schema:about anzsrc-for:08
2 anzsrc-for:0806
3 schema:author N4b875b9bed1c4cd890e436d5390e648f
4 schema:datePublished 2015-09-02
5 schema:datePublishedReg 2015-09-02
6 schema:description Effective and efficient delivery of services requires tasks to be allocated to appropriate and available set of resources. Much of the research in task allocation, model a system of tasks and resources and determine which tasks should be executed by which resources. These techniques when applied to service systems with human resources, model parameters that can be explicitly identified, such as worker efficiency, worker capability based on skills and expertise, authority derived from organizational positions and so on. However, in real-life workers have complex behaviors with varying efficiencies that are either unknown or are increasingly complex to model. Hence, resource allocation models that equate human performance to device or machine performance could provide inaccurate results. In this paper we use data from process execution logs to identify resource allocations that have resulted in an expected service quality, to guide future resource allocations. We evaluate data for a service system with 40 human workers for a period of 8 months. We build a learning model using Support Vector Machine (SVM), that predicts the quality of service for specific allocation of tasks to workers. The SVM based classifier is able to predict service quality with 80 % accuracy. Further, a latent discriminant classifier, uses the number of tasks pending in a worker’s queue as a key predictor, to predict the likelihood of allocating a new incoming request to the worker. A simulation model that incorporates the dispatching policy based on worker’s pending tasks shows an improved service quality and utilization of service workers.
7 schema:editor N04d78d69acc9495faeadf6712371d504
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf Ne92bd14dd1b94d1591915f04d3f6fe61
11 schema:keywords accuracy
12 allocation
13 allocation model
14 authorities
15 available set
16 behavior
17 capability
18 classifier
19 complex behavior
20 data
21 delivery
22 determine
23 devices
24 discriminant classifier
25 efficiency
26 efficient delivery
27 execution logs
28 expertise
29 future resource allocation
30 good quality
31 historical data
32 human performance
33 human resources
34 human workers
35 improved service quality
36 inaccurate results
37 incoming requests
38 key predictors
39 learning model
40 likelihood
41 logs
42 machine
43 machine performance
44 model
45 model parameters
46 months
47 new incoming requests
48 number
49 number of tasks
50 organizational position
51 paper
52 parameters
53 performance
54 period
55 policy
56 position
57 predictors
58 process execution logs
59 quality
60 quality of service
61 queue
62 requests
63 research
64 resource allocation
65 resource allocation model
66 resources
67 results
68 service quality
69 service system
70 service workers
71 services
72 set
73 simulation model
74 skills
75 specific allocation
76 support vector machine
77 system
78 system of tasks
79 task
80 task allocation
81 technique
82 utilization
83 vector machine
84 worker capabilities
85 worker efficiency
86 workers
87 schema:name Learning ‘Good Quality’ Resource Allocations from Historical Data
88 schema:pagination 84-95
89 schema:productId N11efb172867a4160ab5bf73c2041ab0a
90 N9e5e98081b2e45568d94403ee91c26d9
91 schema:publisher N8278eab5de264725a3904b4e9a3d6193
92 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003147418
93 https://doi.org/10.1007/978-3-319-22885-3_8
94 schema:sdDatePublished 2022-12-01T06:49
95 schema:sdLicense https://scigraph.springernature.com/explorer/license/
96 schema:sdPublisher N600dde0c3b4144c7be60bc9a705a231d
97 schema:url https://doi.org/10.1007/978-3-319-22885-3_8
98 sgo:license sg:explorer/license/
99 sgo:sdDataset chapters
100 rdf:type schema:Chapter
101 N03f0906ac1af44faa7ea36f8d23859fd schema:familyName Benslimane
102 schema:givenName Djamal
103 rdf:type schema:Person
104 N04d78d69acc9495faeadf6712371d504 rdf:first N2e64cffaffa440c79624ab71e29556ed
105 rdf:rest N252c3a8703a14289928d811ff660abfc
106 N058f68ef95ba45f890e286bbf6231bf1 rdf:first N7c0ed61c79794862ac605f3eae2d294a
107 rdf:rest Nf011d78d78ad42e99dad3c210bb4012f
108 N11efb172867a4160ab5bf73c2041ab0a schema:name doi
109 schema:value 10.1007/978-3-319-22885-3_8
110 rdf:type schema:PropertyValue
111 N16231e0f392c42faa4eccd5cd16a934f rdf:first N3dbcce4c9b104b71b523b582b794cd76
112 rdf:rest Nedb4e9071edc4123b3579d9caf719d45
113 N1ba29960f86e47c2a13219a409c70e89 rdf:first N8abe61604e0844eab54bebc9cb5dc583
114 rdf:rest rdf:nil
115 N252c3a8703a14289928d811ff660abfc rdf:first Ndd40b27e9caf46ddb71fa49ad0aece57
116 rdf:rest N872b80de6559413f8ba07dc637ed16c4
117 N2e64cffaffa440c79624ab71e29556ed schema:familyName Toumani
118 schema:givenName Farouk
119 rdf:type schema:Person
120 N3dbcce4c9b104b71b523b582b794cd76 schema:familyName Ben Hadj-Alouane
121 schema:givenName Nejib
122 rdf:type schema:Person
123 N4b82fdf745bb4584a725fc95db3033b9 schema:familyName Grigori
124 schema:givenName Daniela
125 rdf:type schema:Person
126 N4b875b9bed1c4cd890e436d5390e648f rdf:first sg:person.015651720511.55
127 rdf:rest N6b14cace067f44f489f85f898b1019eb
128 N600dde0c3b4144c7be60bc9a705a231d schema:name Springer Nature - SN SciGraph project
129 rdf:type schema:Organization
130 N6b14cace067f44f489f85f898b1019eb rdf:first sg:person.015573517335.70
131 rdf:rest Nbe74e73f8dfd40f58a34eb31af687b57
132 N7c0ed61c79794862ac605f3eae2d294a schema:familyName Perrin
133 schema:givenName Olivier
134 rdf:type schema:Person
135 N8278eab5de264725a3904b4e9a3d6193 schema:name Springer Nature
136 rdf:type schema:Organisation
137 N872b80de6559413f8ba07dc637ed16c4 rdf:first N4b82fdf745bb4584a725fc95db3033b9
138 rdf:rest Ne83f712bf6db41f3913258bcea8abf3b
139 N8abe61604e0844eab54bebc9cb5dc583 schema:familyName Bhiri
140 schema:givenName Sami
141 rdf:type schema:Person
142 N9a657d482fc94e9d8101f590cd5d3bf5 rdf:first Nebc5b222d14a476fbdfeacbfaa51298c
143 rdf:rest N16231e0f392c42faa4eccd5cd16a934f
144 N9d26f1dfca834443bdda1bbc31f9107b schema:familyName Saleh Moustafa
145 schema:givenName Iman
146 rdf:type schema:Person
147 N9e5e98081b2e45568d94403ee91c26d9 schema:name dimensions_id
148 schema:value pub.1003147418
149 rdf:type schema:PropertyValue
150 Nb17eb4d822ca4304bc02af3724a20760 schema:familyName Blake
151 schema:givenName Brian
152 rdf:type schema:Person
153 Nbe74e73f8dfd40f58a34eb31af687b57 rdf:first sg:person.011623557301.33
154 rdf:rest rdf:nil
155 Ndd40b27e9caf46ddb71fa49ad0aece57 schema:familyName Pernici
156 schema:givenName Barbara
157 rdf:type schema:Person
158 Ne83f712bf6db41f3913258bcea8abf3b rdf:first N03f0906ac1af44faa7ea36f8d23859fd
159 rdf:rest N9a657d482fc94e9d8101f590cd5d3bf5
160 Ne92bd14dd1b94d1591915f04d3f6fe61 schema:isbn 978-3-319-22884-6
161 978-3-319-22885-3
162 schema:name Service-Oriented Computing - ICSOC 2014 Workshops
163 rdf:type schema:Book
164 Nebc5b222d14a476fbdfeacbfaa51298c schema:familyName Mendling
165 schema:givenName Jan
166 rdf:type schema:Person
167 Nedb4e9071edc4123b3579d9caf719d45 rdf:first Nb17eb4d822ca4304bc02af3724a20760
168 rdf:rest N058f68ef95ba45f890e286bbf6231bf1
169 Nf011d78d78ad42e99dad3c210bb4012f rdf:first N9d26f1dfca834443bdda1bbc31f9107b
170 rdf:rest N1ba29960f86e47c2a13219a409c70e89
171 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
172 schema:name Information and Computing Sciences
173 rdf:type schema:DefinedTerm
174 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
175 schema:name Information Systems
176 rdf:type schema:DefinedTerm
177 sg:person.011623557301.33 schema:affiliation grid-institutes:grid.481550.d
178 schema:familyName Dasgupta
179 schema:givenName Gaargi Banerjee
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011623557301.33
181 rdf:type schema:Person
182 sg:person.015573517335.70 schema:affiliation grid-institutes:grid.1007.6
183 schema:familyName Ghose
184 schema:givenName Aditya
185 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015573517335.70
186 rdf:type schema:Person
187 sg:person.015651720511.55 schema:affiliation grid-institutes:grid.1007.6
188 schema:familyName Sindhgatta
189 schema:givenName Renuka
190 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015651720511.55
191 rdf:type schema:Person
192 grid-institutes:grid.1007.6 schema:alternateName University of Wollongong, Wollongong, NSW, Australia
193 schema:name IBM Research-India, Bangalore, India
194 University of Wollongong, Wollongong, NSW, Australia
195 rdf:type schema:Organization
196 grid-institutes:grid.481550.d schema:alternateName IBM Research-India, Bangalore, India
197 schema:name IBM Research-India, Bangalore, India
198 rdf:type schema:Organization
 




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


...