|
on Big Data |
| By: | Fuster, Andreas; Goldsmith-Pinkham, Paul; Ramadorai, Tarun; Walther, Ansgar |
| Abstract: | Recent innovations in statistical technology, including in evaluating creditworthiness, have sparked concerns about impacts on the fairness of outcomes across categories such as race and gender. We build a simple equilibrium model of credit provision in which to evaluate such impacts. We find that as statistical technology changes, the effects on disparity depend on a combination of the changes in the functional form used to evaluate creditworthiness using underlying borrower characteristics and the cross-category distribution of these characteristics. Employing detailed data on US mortgages and applications, we predict default using a number of popular machine learning techniques, and embed these techniques in our equilibrium model to analyze both extensive margin (exclusion) and intensive margin (rates) impacts on disparity. We propose a basic measure of cross-category disparity, and find that the machine learning models perform worse on this measure than logit models, especially on the intensive margin. We discuss the implications of our findings for mortgage policy. |
| Keywords: | credit access; Machine Learning; Mortgages; statistical discrimination |
| JEL: | G21 G28 R30 |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:cpr:ceprdp:12448&r=big |
| By: | Elisa Letizia; Fabrizio Lillo |
| Abstract: | Understanding the structure of interactions between corporate firms is critical to identify risk concentration and the possible pathways of propagation of financial distress. In this paper we consider the in- teraction due to payments and, by investigating a large proprietary dataset of Italian firms, we characterize the topological properties of the payment network. We then focus on the relation between the net- work of payments and the risk of firms. We show the existence of an homophily of risk, i.e. the tendency of firms with similar risk pro- file to be statistically more connected among themselves. This effect is observed both when considering pairs of firms and when consider- ing communities or hierarchies identified in the network. By applying machine learning techniques, we leverage this knowledge to show that network properties of a node can be used to predict the missing rating of a firm. Our results suggest that risk assessment should take quan- titatively into account also the network of interactions among firms. |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1711.07677&r=big |
| By: | Proto, Eugenio (University of Warwick); Sgroi, Daniel (University of Warwick); Nazneen, Mahnaz (University of Warwick) |
| Abstract: | Existing research supports two opposing mechanisms through which positive mood might affect cooperation. Some studies have suggested that positive mood produces more altruistic, open and helpful behavior, fostering cooperation. However, there is contrasting research supporting the idea that positive mood produces more assertiveness and inward-orientation and reduced use of information, hampering cooperation. We find evidence that suggests the second hypothesis dominates when playing the repeated Prisoner's Dilemma. Players in an induced positive mood tend to cooperate less than players in a neutral mood setting. This holds regardless of uncertainty surrounding the number of repetitions or whether pre-play communication has taken place. This finding is consistent with a text analysis of the pre-play communication between players indicating that subjects in a more positive mood use more inward-oriented, more negative and less positive language. To the best of our knowledge we are the first to use text analysis in pre-play communication. |
| Keywords: | Prisoner's Dilemma, cooperation, positive mood |
| JEL: | C72 C91 D91 |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:iza:izadps:dp11130&r=big |
| By: | Richard Freeman; Wenquan Liang; Ran Song; Christopher Timmins |
| Abstract: | We develop a residential sorting model incorporating migration disutility to recover the implicit value of clean air in China. The model is estimated using China Population Census Data along with PM2.5 satellite data. Our study provides new evidence on the willingness to pay for air quality improvement in developing countries and is the first application of an equilibrium sorting model to the valuation of non-market amenities in China. We employ two novel instrumental variables based on coal-fired electricity generation and wind direction to address the endogeneity of local air pollution. Results suggest important differences between the residential sorting model and a conventional hedonic model, highlighting the role of moving costs and the discreteness of the choice set. Our sorting results indicate that the economic value of air quality improvement associated with a one-unit decline in PM2.5 concentration is up to $8.83 billion for all Chinese households in 2005. |
| JEL: | Q51 Q53 R23 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:24157&r=big |
| By: | Masaya Abe; Hideki Nakayama |
| Abstract: | Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper implements deep learning to predict one-month-ahead stock returns in the cross-section in the Japanese stock market and investigates the performance of the method. Our results show that deep neural networks generally outperform shallow neural networks, and the best networks also outperform representative machine learning models. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section. |
| Date: | 2018–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1801.01777&r=big |
| By: | John Gathergood; Neale Mahoney; Neil Stewart; Joerg Weber |
| Abstract: | We study how individuals repay their debt using linked data on multiple credit cards from five major issuers. We find that individuals do not allocate repayments to the higher interest rate card, which would minimize the cost of borrowing. Instead, individuals allocate repayments using a balance-matching heuristic under which the share of repayments on each card is matched to the share of balances on each card. We show that balance matching captures more than half of the predictable variation in repayments, performs substantially better than other models, and is highly persistent within individuals over time. Consistent with these findings, we show that machine learning algorithms attribute the greatest variable importance to balances and the least variable importance to interest rates in predicting repayment behavior. |
| JEL: | D12 D14 G02 G20 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:24161&r=big |
| By: | Anton Korinek; Joseph E. Stiglitz |
| Abstract: | Inequality is one of the main challenges posed by the proliferation of artificial intelligence (AI) and other forms of worker-replacing technological progress. This paper provides a taxonomy of the associated economic issues: First, we discuss the general conditions under which new technologies such as AI may lead to a Pareto improvement. Secondly, we delineate the two main channels through which inequality is affected – the surplus arising to innovators and redistributions arising from factor price changes. Third, we provide several simple economic models to describe how policy can counter these effects, even in the case of a “singularity” where machines come to dominate human labor. Under plausible conditions, non-distortionary taxation can be levied to compensate those who otherwise might lose. Fourth, we describe the two main channels through which technological progress may lead to technological unemployment – via efficiency wage effects and as a transitional phenomenon. Lastly, we speculate on how technologies to create super-human levels of intelligence may affect inequality and on how to save humanity from the Malthusian destiny that may ensue. |
| JEL: | D63 E64 O3 |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:24174&r=big |
| By: | O. B. Sezer; M. Ozbayoglu; E. Dogdu |
| Abstract: | In this paper, a neural network-based stock price prediction and trading system using technical analysis indicators is presented. The model developed first converts the financial time series data into a series of buy-sell-hold trigger signals using the most commonly preferred technical analysis indicators. Then, a Multilayer Perceptron (MLP) artificial neural network (ANN) model is trained in the learning stage on the daily stock prices between 1997 and 2007 for all of the Dow30 stocks. Apache Spark big data framework is used in the training stage. The trained model is then tested with data from 2007 to 2017. The results indicate that by choosing the most appropriate technical indicators, the neural network model can achieve comparable results against the Buy and Hold strategy in most of the cases. Furthermore, fine tuning the technical indicators and/or optimization strategy can enhance the overall trading performance. |
| Date: | 2017–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1712.09592&r=big |
| By: | Shuheng Wang; Guohao Li; Yifan Bao |
| Abstract: | Application of fuzzy support vector machine in stock price forecast. Support vector machine is a new type of machine learning method proposed in 1990s. It can deal with classification and regression problems very successfully. Due to the excellent learning performance of support vector machine, the technology has become a hot research topic in the field of machine learning, and it has been successfully applied in many fields. However, as a new technology, there are many limitations to support vector machines. There is a large amount of fuzzy information in the objective world. If the training of support vector machine contains noise and fuzzy information, the performance of the support vector machine will become very weak and powerless. As the complexity of many factors influence the stock price prediction, the prediction results of traditional support vector machine cannot meet people with precision, this study improved the traditional support vector machine fuzzy prediction algorithm is proposed to improve the new model precision. NASDAQ Stock Market, Standard & Poor's (S&P) Stock market are considered. Novel advanced- fuzzy support vector machine (NA-FSVM) is the proposed methodology. |
| Date: | 2018–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1801.00681&r=big |
| By: | HAYASHI Susumu |
| Abstract: | Many U.S. artificial intelligence startups regard their technology as a means to augment the capacity of skilled professionals. Artificial intelligence is a kind of intellectual powered exoskeleton, and a professional augmented version with such an intellectual exoskeleton is another type of AI, or augmented intelligence. What really matters is not the "race against the machine" but the "race against the machine-powered human competitor." A highly skilled "AI-master craftsman" in the near future would replace less skilled human workers with artificial workers who work as his/her journeymen or apprentices. In this way, advanced AI technologies will worsen the problem of economic inequality, and destabilize the future society. Entirely new social systems must be studied and introduced to prevent it. A potential scenario could be Chinese workers assembling iPhones in mainland China being replaced by the AI-master craftsman's artificial workers located in the United States. It is even possible that the American AI-master and his team will work for Asian enterprises. Thus, AI might reverse the direction of offshoring. We should prepare for the possibility of such a drastic change in the world economic system caused by the advancement of AI technologies. |
| Date: | 2017–11 |
| URL: | http://d.repec.org/n?u=RePEc:eti:rpdpjp:17033&r=big |