Examining user behavior with machine learning for effective mobile peer-to-peer payment adoption

Antonio, Blanco-Oliver; Juan, Lara-Rubio; Ana, Irimia-Diéguez; Francisco, Liébana-Cabanillas

doi:10.1186/s40854-024-00625-3

Financial Innovation

Table 4 Performance results in out-of-sample

From: Examining user behavior with machine learning for effective mobile peer-to-peer payment adoption

	AUC	Test accuracy	Type I error	Type II error	Sensitivity	Specificity	G-mean	LR-	DP	BA	Youden’s ϓ	WBA1	WBA2	GPI
Panel A. By using the independent variables resulting from feature selection
LDA	0.8911	0.7829	0.2500	0.1919	0.8081	0.7500	0.7785	0.2559	0.6073	0.7791	0.5581	0.7645	0.7936	0.6598
LR	0.8870	0.7714	0.2368	0.2222	0.7778	0.7632	0.7705	0.2911	0.5802	0.7705	0.5410	0.7669	0.7742	0.6465
MLP1	0.8925	0.7829	0.2237	0.2121	0.7879	0.7763	0.7821	0.2732	0.6121	0.7821	0.5642	0.7792	0.7850	0.6610
MLP2	0.8917	0.7771	0.2368	0.2121	0.7879	0.7632	0.7755	0.2779	0.5944	0.7756	0.5511	0.7694	0.7817	0.6536
MLP3	0.8929	0.7771	0.2368	0.2121	0.7879	0.7632	0.7755	0.2779	0.5944	0.7756	0.5511	0.7694	0.7817	0.6537
MLP4	0.8874	0.7829	0.2105	0.2222	0.7778	0.7895	0.7836	0.2814	0.6165	0.7837	0.5673	0.7866	0.7807	0.6613
SVM	0.8957	0.7829	0.2368	0.2020	0.7980	0.7632	0.7804	0.2647	0.6092	0.7806	0.5612	0.7719	0.7893	0.6607
CART	0.7742	0.7657	0.2895	0.1919	0.8081	0.7105	0.7577	0.2701	0.5592	0.7593	0.5186	0.7349	0.7837	0.6274
CTBag	0.8405	0.7486	0.2763	0.2323	0.7677	0.7237	0.7454	0.3210	0.5168	0.7457	0.4914	0.7347	0.7567	0.6136
RF	0.8702	0.7829	0.2105	0.2222	0.7778	0.7895	0.7836	0.2814	0.6165	0.7837	0.5673	0.7866	0.7807	0.6598
AdaBoost	0.8520	0.7829	0.2286	0.2095	0.7905	0.7714	0.7809	0.2716	0.6092	0.7810	0.5619	0.7762	0.7857	0.6564
Binomial Boosting	0.8914	0.7543	0.0132	0.4242	0.5758	0.9868	0.7538	0.4299	1.1062	0.7813	0.5626	0.8841	0.6786	0.6859
L2 Boosting	0.8917	0.7829	0.2237	0.2121	0.7879	0.7763	0.7821	0.2732	0.6121	0.7821	0.5642	0.7792	0.7850	0.6609
Panel B. By using all the independent variables
LDA	0.8826	0.7600	0.2368	0.2424	0.7576	0.7632	0.7604	0.3176	0.5531	0.7604	0.5208	0.7618	0.7590	0.6328
LR	0.8635	0.7771	0.2500	0.2020	0.7980	0.7500	0.7736	0.2693	0.5920	0.7740	0.5480	0.7620	0.7860	0.6504
MLP1	0.8753	0.7829	0.2368	0.2020	0.7980	0.7632	0.7804	0.2647	0.6092	0.7806	0.5612	0.7719	0.7893	0.6588
MLP2	0.8814	0.7886	0.2368	0.1919	0.8081	0.7632	0.7853	0.2514	0.6245	0.7857	0.5713	0.7744	0.7969	0.6662
MLP3	0.8853	0.8000	0.1974	0.2020	0.7980	0.8026	0.8003	0.2517	0.6648	0.8003	0.6006	0.8015	0.7992	0.6819
MLP4	0.8398	0.8057	0.1579	0.2222	0.7778	0.8421	0.8093	0.2639	0.7008	0.8100	0.6199	0.8260	0.7939	0.6874
SVM	0.8846	0.7886	0.1974	0.2222	0.7778	0.8026	0.7901	0.2769	0.6358	0.7902	0.5804	0.7964	0.7840	0.6685
CART	0.8088	0.7600	0.2105	0.2626	0.7374	0.7895	0.7630	0.3326	0.5637	0.7635	0.5269	0.7765	0.7504	0.6279
CTBag	0.8870	0.8000	0.1842	0.2121	0.7879	0.8158	0.8017	0.2600	0.6705	0.8019	0.6037	0.8088	0.7949	0.6829
RF	0.8969	0.8000	0.1974	0.2020	0.7980	0.8026	0.8003	0.2517	0.6648	0.8003	0.6006	0.8015	0.7992	0.6829
AdaBoost	0.8878	0.7886	0.1053	0.2929	0.7071	0.8947	0.7954	0.3274	0.7233	0.8009	0.6018	0.8478	0.7540	0.6795
Binomial Boosting	0.8878	0.7486	0.0132	0.4343	0.5657	0.9868	0.7471	0.4401	1.0963	0.7763	0.5525	0.8815	0.6710	0.6794
L2 Boosting	0.8879	0.7943	0.1842	0.2222	0.7778	0.8158	0.7966	0.2724	0.6563	0.7968	0.5936	0.8063	0.7873	0.6764

Back to article page