Machine Learning and Event-Based Software Testing: Classifiers for Identifying Infeasible GUI Event Sequences

Gove, Robert; Faytong, Jorge

doi:10.1016/b978-0-12-396535-6.00004-1

Cited by 39 publications

(20 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm constructs an optimal hyperplane that correctly classifies data points by separating the points of categories as much as possible [ 79 ]. The closest values to the classification margin are known as support vectors while the goal is to maximize the margin between the hyperplane and the support vectors [ 80 ].…”

Section: Methodsmentioning

confidence: 99%

A machine learning approach to the digitalization of bank customers: Evidence from random and causal forests

2020

View full text Add to dashboard Cite

Understanding the digital jump of bank customers is key to design strategies to bring on board and keep online users, as well as to explain the increasing competition from new providers of financial services (such as BigTech and FinTech). This paper employs a machine learning approach to examine the digitalization process of bank customers using a comprehensive consumer finance survey. By employing a set of algorithms (random forests, conditional inference trees and causal forests) this paper identities the features predicting bank customers’ digitalization process, illustrates the sequence of consumers’ decision-making actions and explores the existence of causal relationships in the digitalization process. Random forests are found to provide the highest performance–they accurately predict 88.41% of bank customers’ online banking adoption and usage decisions. We find that the adoption of digital banking services begins with information-based services (e.g., checking account balance), conditional on the awareness of the range of online services by customers, and then is followed by transactional services (e.g., online/mobile money transfer). The diversification of the use of online channels is explained by the consciousness about the range of services available and the safety perception. A certain degree of complementarity between bank and non-bank digital channels is also found. The treatment effect estimations of the causal forest algorithms confirm causality of the identified explanatory factors. These results suggest that banks should address the digital transformation of their customers by segmenting them according to their revealed preferences and offering them personalized digital services. Additionally, policymakers should promote financial digitalization, designing policies oriented towards making consumers aware of the range of online services available.

show abstract

Section: Methodsmentioning

confidence: 99%

A machine learning approach to the digitalization of bank customers: Evidence from random and causal forests

2020

View full text Add to dashboard Cite

show abstract

“…Gove and Faytong [18] claimed that a model of the GUI may not completely represent the GUI, and therefore may allow infeasible test cases to be generated that violate constraints in the GUI. They used two di®erent machine learning techniques, namely support vector machines and grammar induction, to identify infeasible test cases.…”

Section: Related Workmentioning

confidence: 99%

“…Similarly, it is assumed that the value for biological stage is entered to the biologicalStage variable through the GUI input object comboBox[Biological Stage]. Biological stages are adolescence (12)(13)(14)(15)(16)(17)(18)(19)(20) and adult GUI input contract of Age Application is given in Table 2 with the following assertions:…”

Section: Modeling Gui With Input Contractsmentioning

confidence: 99%

Input Contract Testing of Graphical User Interfaces

Tuğlular

Belli

Linschulte³

2016

Int. J. Soft. Eng. Knowl. Eng.

View full text Add to dashboard Cite

User inputs are critical for the security, safety, and reliability of software systems. This paper proposes a new concept called user input contracts, which is an integral part of a design-bycontract supplemented development process, and a model-based testing approach to detect violations of user input contracts. The approach generates test cases from an input contract integrated with graph-based model of user interface speci¯cation and applies them to the system under consideration. The paper presents a proof-of-concept tool that has been developed and used to validate the approach by experiments. The experiments are conducted on a web-based system for marketing tourist services to analyze input robustness of system under consideration with respect to user input contracts.

show abstract

“…Traditional DTI methods are time-consuming, costly, and make it difficult to obtain three-dimensional structures of compounds and proteins [ 6 , 7 , 8 ]. The technology of machine learning accelerates the development of drug–target interactions, especially in reducing the blindness of experiments [ 9 , 10 , 11 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs

Wang

Zhang

Chen

et al. 2021

IJMS

View full text Add to dashboard Cite

Backgroud: The prediction of drug–target interactions (DTIs) is of great significance in drug development. It is time-consuming and expensive in traditional experimental methods. Machine learning can reduce the cost of prediction and is limited by the characteristics of imbalanced datasets and problems of essential feature selection. Methods: The prediction method based on the Ensemble model of Multiple Feature Pairs (Ensemble-MFP) is introduced. Firstly, three negative sets are generated according to the Euclidean distance of three feature pairs. Then, the negative samples of the validation set/test set are randomly selected from the union set of the three negative sets in the validation set/test set. At the same time, the ensemble model with weight is optimized and applied to the test set. Results: The area under the receiver operating characteristic curve (area under ROC, AUC) in three out of four sub-datasets in gold standard datasets was more than 94.0% in the prediction of new drugs. The effectiveness of the proposed method is also shown with the comparison of state-of-the-art methods and demonstration of predicted drug–target pairs. Conclusion: The Ensemble-MFP can weigh the existing feature pairs and has a good prediction effect for general prediction on new drugs.

show abstract

Machine Learning and Event-Based Software Testing: Classifiers for Identifying Infeasible GUI Event Sequences

Cited by 39 publications

References 12 publications

A machine learning approach to the digitalization of bank customers: Evidence from random and causal forests

A machine learning approach to the digitalization of bank customers: Evidence from random and causal forests

Input Contract Testing of Graphical User Interfaces

Predicting Drug–Target Interactions Based on the Ensemble Models of Multiple Feature Pairs

Contact Info

Product

Resources

About