Skip to main content

Table 1 Summary of call prediction studies including dataset, evaluation method, prediction accuracy, and predicted channel i.e. call, text, or both. Here, it can be clearly seen that all proposed algorithms so far only target a single channel, i.e. calls

From: Text and phone calls: user behaviour and dual-channel communication prediction

Study Dataset Evaluation matrics Channel
Call Text
Phithakkitnu-koon et al. (94) Users reality mining project Accuracy 70% \(\checkmark \) \(\times \)
Phithakkitnu-koon et al. (20) Users False positive = 2.4% false negative = 2.9% error rate= 5.4% \(\checkmark \) \(\times \)
Haddad et al. (7645) users Mean absolute error = 69 proportion of calls predicted within less than 1h = 17.4 % \(\checkmark \) \(\times \)
Barzaiq et al. Synthetic data (1, 143) calls reality mining (5, 484) calls Accuracy 35% \(\checkmark \) \(\times \)
Nasim et al. Smartphone (786) users reality mining Accuracy 78% \(\checkmark \) \(\times \)
Stefanis et al. Reality mining project Accuracy 80% \(\checkmark \) \(\times \)
Lee et al. (20) users Accuracy: group A > 75% other users < 50% \(\checkmark \) \(\times \)
Sarker et al. Reality mining (5) users F-measure 0.8 \(\checkmark \) \(\times \)
Fatima et al. Smartphone (786) users MDC (522) users Accuracy: MDC 85% Smartphone 56% \(\checkmark \) \(\times \)