BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20191025T103514Z
DTSTART:20191211T140000Z
DTEND:20191211T150000Z
SUMMARY:Mercury Talk: Data-Driven Modelling of Technology Acceptance: A M
 achine Learning Perspective
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}di-k2601ihm
 -j3bt6p
DESCRIPTION:Join us for the next Computer Science Mercury Talk with speak
 er Asim Alwabel in Kilburn L.T 1.5\n\n\nForecasting and understanding te
 chnology adoption have dominated research of Information Systems (IS) fo
 r more than two decades. Although structural equation modelling is suita
 ble for explanatory modelling\, it was regarded by majority of IS resear
 ch as a predictive technique. On the other hand\, despite development an
 d utility of predictive analytics\, its use in estimating technology usa
 bility remains scarce. This research demonstrates a unique data driven a
 pproach utilising linear and non-linear machine learning (ML) techniques
 \, predictive analytics-based modelling\, to advance technology adoption
  modelling\, assess its predictability\, evaluate relevance of its curre
 nt determinants\, and introduce new ones. Inspired by current literature
 \, the resulting model comprised 37 features and was tested on 32 techno
 logies with heterogeneous subjects. Content validity of the model was at
 tained applying Twitter API\, text-mining technique and interviews. Befo
 re modelling\, the discriminant validity was accomplished applying multi
 trait-multimethod analysis. Performance of the proposed model was estima
 ted employing multiple linear regression\, k-nearest neighbour\, decisio
 n tree\, multilayer perceptron\, and support vector machine with mean ab
 solute percentage error as loss metric. The model was benchmarked agains
 t the current literature to highlight differences and similarities. As a
  result\, ML-based modelling revealed the distance between theory and pr
 actice.\n\n\n
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:L.T 1.5\, Kilburn Building\, Manchester
END:VEVENT
END:VCALENDAR