The Credit Scoring Model Based on Logistic-BP-AdaBoost Algorithm and its Application in P2P Credit Platform

apply the Logistics algorithm, BP neural network and the AdaBoost algorithm to
build the model (Logistic-BP-AdaBoost model) which can estimate credit score of
the applicant with their multidimensional personal data. Compared with other
the possibility of loan default of the applicant and provide a score for each applicant.
We apply this model to a websites and establish an online loan platform which
is expected to improve the efficiency and reduce costs of traditional lending
business.
Conclusion: Based on the data mining technology and learned other researchers’ achievements, we studied the methods of logistic regression, BP neural network and AdaBoost, and improve complex approval work and reduce prediction error for the traditional loan. In this paper we combine logistic regression with BP neural network and then we use AdaBoost to intensify the model. For the traditional loan approval problem, we fully consider the user registration information and user sources to more accurately predict user success rate for the loan. According to the user multidimensional messages, we can clearly know the users, furthermore, through analyzing the sources of users as well as the user fraud score, we can make accurate judgment to user. Finally L-B-A model was used to the P2P loan platform, and the practice proved that model had high practicability and can achieve the purpose of simplifying the loan approval process.
The Credit Scoring Model Based on Logistic-BP-AdaBoost Algorithm and its Application in P2P Credit Platform

Sim, você deveria entender o backpropagation!

Por Andrej Karpathy

Backpropagation is a leaky abstraction; it is a credit assignment scheme with non-trivial consequences. If you try to ignore how it works under the hood because “TensorFlow automagically makes my networks learn”, you will not be ready to wrestle with the dangers it presents, and you will be much less effective at building and debugging neural networks.
The good news is that backpropagation is not that difficult to understand, if presented properly. I have relatively strong feelings on this topic because it seems to me that 95% of backpropagation materials out there present it all wrong, filling pages with mechanical math. Instead, I would recommend the CS231n lecture on backprop which emphasizes intuition (yay for shameless self-advertising). And if you can spare the time, as a bonus, work through the CS231n assignments, which get you to write backprop manually and help you solidify your understanding.

Sim, você deveria entender o backpropagation!

Unsupervised Feature Learning and Deep Learning

Para quem tem interesse em técnicas de mineração de dados utilizando aprendizado não supervisionado, esse é um ótimo site onde há alguns tutoriais sobre o assunto e algumas técnicas bastante interessantes com as representações matemáticas e com a apliação de cada tipo de algoritmo.

Unsupervised Feature Learning and Deep Learning