𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Response models based on bagging neural networks

✍ Scribed by Kyoungnam Ha; Sungzoon Cho; Douglas MacLachlan

Publisher
John Wiley and Sons
Year
2005
Tongue
English
Weight
217 KB
Volume
19
Category
Article
ISSN
1094-9968

No coin nor oath required. For personal study only.

✦ Synopsis

Identifying customers who are likely to respond to a product offering is an important issue in direct marketing.Response models are typically built from historical purchase data. A popular method of choice, logistic regression, is easy to understand and build, but limited in that the model is linear in parameters. Neural networks are nonlinear and have been found to improve predictive accuracies for a variety of business applications. Neural networks have not always demonstrated clear supremacy over traditional statistics competitors, largely because of over-fitting and instability. Combining multiple networksmay alleviate these problems. A systematic method of combining neural networks is proposed, namely bagging or bootstrap aggregating, whereby overfitted multiple neural networks are trained with bootstrap replicas of the original data set and then averaged. We built response models using a publicly available DMEF data set with three methods: bagging neural networks, single neural networks, and conventional logistic regression. The proposed method not only improved but also stabilized the prediction accuracies over the other two.

πŸ“œ SIMILAR VOLUMES

Higher-order Petri net models based on a
Higher-order Petri net models based on artificial neural networks
✍ Tommy W.S. Chow; Jin-Yan Li πŸ“‚ Article πŸ“… 1997 πŸ› Elsevier Science 🌐 English βš– 720 KB

In this paper, the properties of higher-order neural networks are exploited in a new class of Petri nets, called higher-order Petri nets (HOPN). Using the similarities between neural networks and Petri nets this paper demonstrates how the McCullock-Pitts models and the higher-order neural networks c

Simple models based on neural networks f
Simple models based on neural networks for suspended and inverted microstrip lines
✍ Celal Yildiz; Oytun Saracoglu πŸ“‚ Article πŸ“… 2003 πŸ› John Wiley and Sons 🌐 English βš– 109 KB

## Abstract This paper presents new and simple models based on artificial neural networks (ANNs) to determine the effective permittivities of suspended microstrip (SM) and inverted microstrip (IM) lines. The neural results are in very good agreement with the theoretical and experimental results ava

Temperature-dependent models of low-nois
Temperature-dependent models of low-noise microwave transistors based on neural networks
✍ Zlatica D. MarinkoviΔ‡; Vera V. MarkoviΔ‡ πŸ“‚ Article πŸ“… 2005 πŸ› John Wiley and Sons 🌐 English βš– 545 KB

Neural networks are proposed for efficient temperature-dependent modeling of small-signal and noise performances of low-noise microwave transistors over a wide temperature range. The proposed models can be based either on neural networks only or on a combination of neural networks and empirical tran

Minimax classifiers based on neural netw
Minimax classifiers based on neural networks
✍ RocΓ­o Alaiz-RodrΓ­guez; Alicia Guerrero-Curieses; JesΓΊs Cid-Sueiro πŸ“‚ Article πŸ“… 2005 πŸ› Elsevier Science 🌐 English βš– 247 KB