2021
DOI: 10.1016/j.mlwa.2021.100074
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning algorithms for fraud prediction in property insurance: Empirical evidence using real-world microdata

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
20
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 45 publications
(22 citation statements)
references
References 33 publications
1
20
0
1
Order By: Relevance
“…By using the method, we have used in this paper, Automobile Insurance companies can imply this method to monitor the leakage of claims where scammers sometimes overstate or fabricate incidents in order to support fraudulent claims [14,15].…”
Section: Discussionmentioning
confidence: 99%
“…By using the method, we have used in this paper, Automobile Insurance companies can imply this method to monitor the leakage of claims where scammers sometimes overstate or fabricate incidents in order to support fraudulent claims [14,15].…”
Section: Discussionmentioning
confidence: 99%
“…Recent examples of gradient boosting machine applications for time series prediction can be seen in Johnson et al (2017) and Lopez‐Martin et al (2019); specifically for COVID‐19 data, this method was applied in Haimovich et al (2020) and Malki et al (2020). Specifically for financial problems, recent works include Gumelar et al (2020), which compared XGBoost with Long Short‐Term Memory (LSTM) neural networks for stock price prediction using data from 25 companies listed in the Indonesia Stock Exchange; Jabeur et al (2021), which compared two GBM variants (XGBoost and CatBoost) to forecast the time series of gold price data; and Severino and Peng (2021), which compared GBM with eight other machine learning models for the fraud detection task using real‐world microdata using eXplainable Artificial Intelligence (XAI) methods to evaluate the most relevant features at both global and local levels.…”
Section: Boosting Modelsmentioning
confidence: 99%
“…It was thanks to the contract on sharable elements that designers and engineers from industry and academia across the data processing pile were able to innovate at both system level (TPU, convolutional core GPU on a microprocessor), as well as at the system level (a pervasiveness of architectures constructed on common libraries, such as PyTorch, Machine learning, Horovod and others). Identifying the correct abstract concepts for a particular domain is challenging, but the potential reward is enormous because they can activate advancement along multiple integrations [10].…”
Section: Domain-specific Designsmentioning
confidence: 99%