ABSTRACT
Neural networks (NNs) are an immensely rich and complicated topic. In this chapter, the authors introduce the simple ideas and concepts behind the most simple architectures of NNs. Early references of neural networks in finance are Bansal and Viswanathan and Eakins et al. Both have very different goals. In the first one, the authors aim to estimate a nonlinear form for the pricing kernel. In the second one, the purpose is to identify and quantify relationships between institutional investments in stocks and the attributes of the firm. A perceptron can be viewed as a linear model to which is applied a particular function: the Heaviside function. Other choices of functions are naturally possible. In the NN jargon, they are called activation functions. Their purpose is to introduce nonlinearity in otherwise very linear models.
