In the last decade, high profile financial frauds committed by large companies in both developed and developing countries were discovered and reported. This study compares the performance of five popular statistical and machine learning models in detecting financial statement fraud. The research objects are companies which experienced both fraudulent and non-fraudulent financial statements betw...

In this paper, a single-product, single-machine system under Markovian deterioration of machine condition and demand uncertainty is studied.  The objective is to find the optimal intervals for inspection and preventive maintenance activities in a condition-based maintenance planning with discrete monitoring framework. At first, a stochastic dynamic programming model whose state variable is the ...

Revealing hidden features in unlabeled data is called unsupervised feature learning, which plays an important role in pretraining a deep neural network. Here we provide a statistical mechanics analysis of the unsupervised learning in a restricted Boltzmann machine with binary synapses. A message passing equation to infer the hidden feature is derived, and furthermore, variants of this equation ...

To assist in the research of social networks in history, we develop machine-learning-based tools for the identification and classification of personal relationships. Our case study focuses on the Dutch social movement between 1870 and 1940, and is based on biographical texts describing the lives of notable people in this movement. We treat the identification and the labeling of relations betwee...

The Liquid State Machine (LSM) is a relatively new recurrent neural network architecture, in which a static recurrent spiking neural network referred to as a ‘liquid’ and a trainable read-out network are combined to tackle time-series data. In this paper we describe the Democratic Liquid State Machine (DLSM) that uses an ensemble of single LSMs. We investigated the feasibility of the two LSM ar...