In this paper, we propose a neural network-based method for CVA computations of a portfolio of derivatives. In particular, we focus on portfolios consisting of a combination of derivatives, with and without true optionality, \textit{e.g.,} a portfolio of a mix of European- and Bermudan-type derivatives. CVA is computed, with and without netting, for different levels of WWR and for different levels of credit quality of the counterparty. We show that the CVA is overestimated with up to 25\% by using the standard procedure of not adjusting the exercise strategy for the default-risk of the counterparty. For the Expected Shortfall of the CVA dynamics, the overestimation was found to be more than 100\% in some non-extreme cases.

Discrete-choice life cycle models can be used to, e.g., estimate how social security reforms change employment rate. Optimal employment choices during the life course of an individual can be solved in the framework of life cycle models. This enables estimating how a social security reform influences employment rate. Mostly, life cycle models have been solved with dynamic programming, which is not feasible when the state space is large, as often is the case in a realistic life cycle model. Solving such life cycle models requires the use of approximate methods, such as reinforced learning algorithms. We compare how well a deep reinforced learning algorithm ACKTR and dynamic programming solve a relatively simple life cycle model. We find that the average utility is almost the same in both algorithms, however, the details of the best policies found with different algorithms differ to a degree. In the baseline model representing the current Finnish social security scheme, we find that reinforced learning yields essentially as good results as dynamics programming. We then analyze a straight-forward social security reform and find that the employment changes due to the reform are almost the same. Our results suggest that reinforced learning algorithms are of significant value in analyzing complex life cycle models.

Basic broadband connectivity is regarded as generally having a positive macroeconomic effect. However, over the past decade there has been an emerging school of thought suggesting the impacts of upgrading to higher speed broadband have been overstated, potentially leading to the inefficient allocation of taxpayer-funded subsidies. In this analysis we model the impacts of Next Generation Access on new business creation using high-resolution panel data. After controlling for a range of factors, the results provide evidence of a small but significant negative impact of high-speed broadband on new business creation over the study period which we suggest could be due to two factors. Firstly, moving from basic to high-speed broadband provides few benefits to enable new businesses being formed. Secondly, strong price competition and market consolidation from online service providers (e.g. Amazon etc.) may be deterring new business start-ups. This analysis provides another piece of evidence to suggest that the economic impact of broadband is more nuanced than the debate has traditionally suggested. Our conjecture is that future policy decisions need to be more realistic about the potential economic impacts of broadband, including those effects that could be negative on the stock of local businesses and therefore the local tax base.

In recent years, bankruptcy forecasting has gained lot of attention from researchers as well as practitioners in the field of financial risk management. For bankruptcy prediction, various approaches proposed in the past and currently in practice relies on accounting ratios and using statistical modeling or machine learning methods.These models have had varying degrees of successes. Models such as Linear Discriminant Analysis or Artificial Neural Network employ discriminative classification techniques. They lack explicit provision to include prior expert knowledge. In this paper, we propose another route of generative modeling using Expert Bayesian framework. The biggest advantage of the proposed framework is an explicit inclusion of expert judgment in the modeling process. Also the proposed methodology provides a way to quantify uncertainty in prediction. As a result the model built using Bayesian framework is highly flexible, interpretable and intuitive in nature. The proposed approach is well suited for highly regulated or safety critical applications such as in finance or in medical diagnosis. In such cases accuracy in the prediction is not the only concern for decision makers. Decision makers and other stakeholders are also interested in uncertainty in the prediction as well as interpretability of the model. We empirically demonstrate these benefits of proposed framework using Stan, a probabilistic programming language. We found that the proposed model is either comparable or superior to other existing methods. Also resulting model has much less False Positive Rate compared to many existing state of the art methods. The corresponding R code for the experiments is available at Github repository.

We study the expected utility maximization problem of a large investor who is allowed to make transactions on a tradable asset in a financial market with endogenous permanent market impacts as suggested in [24] building on [6, 7]. The asset price is assumed to follow a nonlinear price curve quoted in the market as the utility indifference curve of a representative liquidity supplier. We show that optimality can be fully characterized via a system of coupled forward-backward stochastic differential equations (FBSDEs) which is equivalent to a highly non-linear backward stochastic partial differential equation (BSPDE). Existence results can be achieved in the case where the driver function of the representative market maker is quadratic or the utility function of the large investor is exponential. Explicit examples are provided when the market is complete or the driver function is positively homogeneous.

The lack of interpretability and transparency are preventing economists from using advanced tools like neural networks in their empirical work. In this paper, we propose a new class of interpretable neural network models that can achieve both high prediction accuracy and interpretability in regression problems with time series cross-sectional data. Our model can essentially be written as a simple function of a limited number of interpretable features. In particular, we incorporate a class of interpretable functions named persistent change filters as part of the neural network. We apply this model to predicting individual's monthly employment status using high-dimensional administrative data in China. We achieve an accuracy of 94.5% on the out-of-sample test set, which is comparable to the most accurate conventional machine learning methods. Furthermore, the interpretability of the model allows us to understand the mechanism that underlies the ability for predicting employment status using administrative data: an individual's employment status is closely related to whether she pays different types of insurances. Our work is a useful step towards overcoming the "black box" problem of neural networks, and provide a promising new tool for economists to study administrative and proprietary big data.

In this paper, we obtain the existence, uniqueness and positivity of the solution to delayed stochastic differential equations with jumps. This equation is then applied to model the price movement of the risky asset in a financial market and the Black-Scholes formula for the price of European options is obtained together with the hedging portfolios. The option price is evaluated analytically at the last delayed period by using the Fourier transformation technique. But in general, there is no analytical expression for the option price. To evaluate the price numerically we then use the Monte-Carlo method. To this end, we need to simulate the delayed stochastic differential equations with jumps. We propose a logarithmic Euler-Maruyama scheme to approximate the equation and prove that all the approximations remain positive and the rate of convergence of the scheme is proved to be $0.5$.

We propose a novel approach to infer investors' risk preferences from their portfolio choices, and then use the implied risk preferences to measure the efficiency of investment portfolios. We analyze a dataset spanning a period of six years, consisting of end of month stock trading records, along with investors' demographic information and self-assessed financial knowledge. Unlike estimates of risk aversion based on the share of risky assets, our statistical analysis suggests that the implied risk aversion coefficient of an investor increases with her wealth and financial literacy. Portfolio diversification, Sharpe ratio, and expected portfolio returns correlate positively with the efficiency of the portfolio, whereas a higher standard deviation reduces the efficiency of the portfolio. We find that affluent and financially educated investors as well as those holding retirement related accounts hold more efficient portfolios.

Designing robust and accurate predictive models for stock price prediction has been an active area of research for a long time. While on one side, the supporters of the efficient market hypothesis claim that it is impossible to forecast stock prices accurately, many researchers believe otherwise. There exist propositions in the literature that have demonstrated that if properly designed and optimized, predictive models can very accurately and reliably predict future values of stock prices. This paper presents a suite of deep learning based models for stock price prediction. We use the historical records of the NIFTY 50 index listed in the National Stock Exchange of India, during the period from December 29, 2008 to July 31, 2020, for training and testing the models. Our proposition includes two regression models built on convolutional neural networks and three long and short term memory network based predictive models. To forecast the open values of the NIFTY 50 index records, we adopted a multi step prediction technique with walk forward validation. In this approach, the open values of the NIFTY 50 index are predicted on a time horizon of one week, and once a week is over, the actual index values are included in the training set before the model is trained again, and the forecasts for the next week are made. We present detailed results on the forecasting accuracies for all our proposed models. The results show that while all the models are very accurate in forecasting the NIFTY 50 open values, the univariate encoder decoder convolutional LSTM with the previous two weeks data as the input is the most accurate model. On the other hand, a univariate CNN model with previous one week data as the input is found to be the fastest model in terms of its execution speed.

We consider a consumption-investment problem in which the investor has an access to the bond market. In our approach prices of bonds with different maturities are described by the general HJM factor model. We assume that the bond market consist of entire family of rolling bonds and the investment strategy is a general signed measure distributed on all real numbers representing time to maturity specifications for different rolling bonds. The investor's objective is to maximize time-additive utility of the consumption process. We solve the problem by means of the HJB equation for which we prove required regularity of its solution and all required estimates to ensure applicability of the verification theorem. Explicit calculations for certain particular models are presented.