Research articles for the 2020-02-16

A New Financial Metric for the Art Market
Charlin, Ventura,Cifuentes, Arturo
This paper introduces a new financial metric for the art market. The metric, which we call Artistic Power Value (APV), is based on the price per unit of area (dollars per square centimeter) and is applicable to two-dimensional art objects such as paintings. In addition to its intuitive appeal and ease of computation, this metric has several advantages from the investor’s viewpoint. It makes it easy to: (i) estimate price ranges for different artists; (ii) perform comparisons among them; (iii) follow the evolution of the artists’ creativity cycle overtime; and (iiii) compare, for a single artist, paintings with different subjects or different geometric properties. Additionally, the APV facilitates the process of estimating total returns. Finally, due to its transparency, the APV can be used to design derivatives-like instruments that can appeal to both, investors and speculators. Several examples validate this metric and demonstrate its usefulness.

Behavior Revealed in Mobile Phone Usage Predicts Loan Repayment
Daniel Björkegren,Darrell Grissen

Many households in developing countries lack formal financial histories, making it difficult for firms to extend credit, and for potential borrowers to receive it. However, many of these households have mobile phones, which generate rich data about behavior. This article shows that behavioral signatures in mobile phone data predict default, using call records matched to repayment outcomes for credit extended by a South American telecom. On a sample of individuals with (thin) financial histories, our method actually outperforms models using credit bureau information, both within time and when tested on a different time period. But our method also attains similar performance on those without financial histories, who cannot be scored using traditional methods. Individuals in the highest quintile of risk by our measure are 2.8 times more likely to default than those in the lowest quintile. The method forms the basis for new forms of credit that reach the unbanked.

Comments are welcome
Asier Minondo

Scholars present their new research at seminars and conferences, and send drafts to peers, hoping to receive comments and suggestions that will improve the quality of their work. Using a dataset of papers published in economics journals, this article measures how much peers' individual and collective comments improve the quality of research. Controlling for the quality of the research idea and author, I find that a one standard deviation increase in the number of peers' individual and collective comments increases the quality of the journal in which the research is published by 47%.

Deep Learning for Financial Applications : A Survey
Ahmet Murat Ozbayoglu,Mehmet Ugur Gudelek,Omer Berat Sezer

Computational intelligence in finance has been a very popular topic for both academia and financial industry in the last few decades. Numerous studies have been published resulting in various models. Meanwhile, within the Machine Learning (ML) field, Deep Learning (DL) started getting a lot of attention recently, mostly due to its outperformance over the classical models. Lots of different implementations of DL exist today, and the broad interest is continuing. Finance is one particular area where DL models started getting traction, however, the playfield is wide open, a lot of research opportunities still exist. In this paper, we tried to provide a state-of-the-art snapshot of the developed DL models for financial applications, as of today. We not only categorized the works according to their intended subfield in finance but also analyzed them based on their DL models. In addition, we also aimed at identifying possible future implementations and highlighted the pathway for the ongoing research within the field.

Economic complexity of prefectures in Japan
Abhijit Chakraborty,Hiroyasu Inoue,Yoshi Fujiwara

Every nation prioritizes the inclusive economic growth and development of all regions. However, we observe that economic activities are clustered in space, which results in a disparity in per-capita income among different regions. A complexity-based method was proposed by Hidalgo and Hausmann [PNAS 106, 10570-10575 (2009)] to explain the large gaps in per-capita income across countries. Although there have been extensive studies on countries' economic complexity using international export data, studies on economic complexity at the regional level are lacking. Here, we study the industrial sector complexity of prefectures in Japan based on the basic information of more than one million firms. We aggregate the data as a bipartite network of prefectures and industrial sectors. We decompose the bipartite network as a prefecture-prefecture network and sector-sector network, which reveals the relationships among them. Similarities among the prefectures and among the sectors are measured using a metric. From these similarity matrices, we cluster the prefectures and sectors using the minimal spanning tree technique. The computed economic complexity index from the structure of the bipartite network shows a high correlation with macroeconomic indicators, such as per-capita gross prefectural product and prefectural income per person. We argue that this index reflects the present economic performance and hidden potential of the prefectures for future growth.

Gaussian process imputation of multiple financial series
Taco de Wolff,Alejandro Cuevas,Felipe Tobar

In Financial Signal Processing, multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market and therefore they are required to be jointly analysed. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process (MOGP) with expressive covariance functions. Learning these market dependencies among financial series is crucial for the imputation and prediction of financial observations. The proposed model is validated experimentally on two real-world financial datasets for which their correlations across channels are analysed. We compare our model against other MOGPs and the independent Gaussian process on real financial data.

Improving S&P stock prediction with time series stock similarity
Lior Sidi

Stock market prediction with forecasting algorithms is a popular topic these days where most of the forecasting algorithms train only on data collected on a particular stock. In this paper, we enriched the stock data with related stocks just as a professional trader would have done to improve the stock prediction models. We tested five different similarities functions and found co-integration similarity to have the best improvement on the prediction model. We evaluate the models on seven S&P stocks from various industries over five years period. The prediction model we trained on similar stocks had significantly better results with 0.55 mean accuracy, and 19.782 profit compare to the state of the art model with an accuracy of 0.52 and profit of 6.6.

Linear-Betas in the Cross-Section of Returns
Douglas, Reed
This paper evaluates a specification for conditional beta models following Fama and French (2019). In this paper, I reject the Fama and French model that assumes characteristics are conditional betas in favor of a linear conditional beta model following Shanken (1990). Model-implied zero-beta rates are particularly sensitive to the specification, and the linear conditional beta model provides a significantly lower rate. Out-of-sample tests show that the Linear-Beta Model has a significantly lower bias and Clark and West (2007) adjusted MSPE, but it may come at the cost of a larger variance than the Fama and French model.

Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Yunan Ye,Hengzhi Pei,Boxin Wang,Pin-Yu Chen,Yada Zhu,Jun Xiao,Bo Li

Portfolio management (PM) is a fundamental financial planning task that aims to achieve investment goals such as maximal profits or minimal risks. Its decision process involves continuous derivation of valuable information from various data sources and sequential decision optimization, which is a prospective research direction for reinforcement learning (RL). In this paper, we propose SARL, a novel State-Augmented RL framework for PM. Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity -- the collected information for each asset is usually diverse, noisy and imbalanced (e.g., news articles); and (2) environment uncertainty -- the financial market is versatile and non-stationary. To incorporate heterogeneous data and enhance robustness against environment uncertainty, our SARL augments the asset information with their price movement prediction as additional states, where the prediction can be solely based on financial data (e.g., asset prices) or derived from alternative sources such as news. Experiments on two real-world datasets, (i) Bitcoin market and (ii) HighTech stock market with 7-year Reuters news articles, validate the effectiveness of SARL over existing PM approaches, both in terms of accumulated profits and risk-adjusted profits. Moreover, extensive simulations are conducted to demonstrate the importance of our proposed state augmentation, providing new insights and boosting performance significantly over standard RL-based PM method and other baselines.

Reputation, Price, and Death: An Empirical Analysis of Art Price Formation
Ursprung, Heinrich W.,Wiermann, Christian
We analyze how an artist's death influences the market prices of her works of art. Death has two opposing effects on art prices. By irrevocably restricting the artist's oeuvre, prices, ceteris paribus, increase when the artist dies. On the other hand, an untimely death may well frustrate the collectors' hopes of owning artwork that will, as the artist's career progresses, become generally known and appreciated. By frustrating expected future name recognition, death impacts negatively on art prices. In conjunction, these two channels of influence give rise to a hump-shaped relationship between age at death and death-induced price changes. Using transactions from fine art auctions, we show that the empirically identified death effects indeed conform to our theoretical predictions. We derive our results from hedonic art price regressions, making use of a data set which exceeds the sample size of traditional studies in cultural economics by an order of magnitude.

Star Artists and Herding in Fine Arts’ Market: Theory and Empirical Evidence
Azarmi, Ted F.,Menny, Philipp R. P.
This paper uses information cascades theory to analyze the art market. It focus on the art stars, explaining the phenomenon that in the art market a small fraction of artists accounts for most of the trade and dominate the financial activity. We analyze fine art auction data. In particular, we draw a Lorenz-curve for the distribution of auction volume (number of works times auction price) in three art market segments. Our auction data demonstrates that a relatively small fraction of artists account for a large portion of the art auction volume. We provide empirical evidence for our theory of herding behavior in fine arts markets. Our data shows that historical auction performance of an artist is significantly more influential in determining the artist’s success than the quality of her work. In particular, our theory and empirical evidence suggests that contemporary artists and less-established ones are subject to more herding behavior than 400 highest ranked artists.

The Effect of Network Adoption Subsidies: Evidence from Digital Traces in Rwanda
Daniel Björkegren,Burak Ceyhun Karaca

Governments spend billions of dollars subsidizing the adoption of different goods. However, it is difficult to gauge whether those goods are resold, or are valued by their ultimate recipients. This project studies a program to subsidize the adoption of mobile phones in one of the poorest countries in the world. Rwanda subsidized the equivalent of 8% of the stock of mobile phones for select rural areas. We analyze the program using 5.3 billion transaction records from the dominant mobile phone network. Transaction records reveal where and how much subsidized handsets were ultimately used, and indicators of resale. Some subsidized handsets drifted from the rural areas where they were allocated to urban centers, but the subsidized handsets were used as much as handsets purchased at retail prices, suggesting they were valued. Recipients are similar to those who paid for phones, but are highly connected to each other. We then simulate welfare effects using a network demand system that accounts for how each person's adoption affects the rest of the network. Spillovers are substantial: 73-76% of the operator revenue generated by the subsidy comes from nonrecipients. We compare the enacted subsidy program to counterfactual targeting based on different network heuristics.

The Price of Color in Mark Rothko’s Paintings
Charlin, Ventura,Cifuentes, Arturo
The relationship between prices of paintings at public auctions and their attributes has received much attention in recent years. However, the effects of color have been mostly absent from these studies. The present study explored the relationship between price and color in Rothko’s post 1950 paintings, which were dominated by color rather than figurative elements. We characterized the color features of the paintings in terms of their dominant hues and luminosity. In addition, we developed two additional metrics to evaluate color contrast, and palette diversity. We found that in general the market favored diverse color compositions, and preferred reds over greens, blues over yellows, and lighter-colored paintings. We also identified two distinct price regimes in the period studied: a first period, dominated by enthusiasm for the artist, regardless of the painting’s characteristics; and a second period, driven by color-related attributes.