Research articles for the 2021-02-09

A Modularized and Scalable Multi-Agent Reinforcement Learning-based System for Financial Portfolio Management
Zhenhan Huang,Fumihide Tanaka

Financial Portfolio Management is one of the most applicable problems in Reinforcement Learning (RL) by its sequential decision-making nature. Existing RL-based approaches, while inspiring, often lack scalability, reusability, or profundity of intake information to accommodate the ever-changing capital markets. In this paper, we design and develop MSPM, a novel Multi-agent Reinforcement learning-based system with a modularized and scalable architecture for portfolio management. MSPM involves two asynchronously updated units: Evolving Agent Module (EAM) and Strategic Agent Module (SAM). A self-sustained EAM produces signal-comprised information for a specific asset using heterogeneous data inputs, and each EAM possesses its reusability to have connections to multiple SAMs. A SAM is responsible for the assets reallocation of a portfolio using profound information from the EAMs connected. With the elaborate architecture and the multi-step condensation of the volatile market information, MSPM aims to provide a customizable, stable, and dedicated solution to portfolio management that existing approaches do not. We also tackle data-shortage issue of newly-listed stocks by transfer learning, and validate the necessity of EAM. Experiments on 8-year U.S. stock markets data prove the effectiveness of MSPM in profits accumulation by its outperformance over existing benchmarks.

Armenia’s Social Policy Response to COVID-19: Mitigating Expectations, Financial Stress, and Anxiety
Aslanyan, Gurgen,Baghdasaryan, Vardan,Shakhmuradyan, Gayane
This report examines the social policy response of the Government of Armenia to the COVID-19 crisis. Official data on the implemented programs suggest that since March 2020, around USD 55 million has been transferred to individuals and households as wage support, unemployment and family benefits, utility payment subsidies and tuition fee support. Survey data suggest that despite being early and extensive, government assistance has not been effective in relieving the financial stress and anxiety caused by the pandemic, while public expectations about the future remain pessimistic. As individuals most and least in need have benefited equally from the implemented programs, government assistance has also not been well-targeted.

Asymmetric Tsallis distributions for modelling financial market dynamics
Sandhya Devi

Financial markets are highly non-linear and non-equilibrium systems. Earlier works have suggested that the behavior of market returns can be well described within the framework of non-extensive Tsallis statistics or superstatistics. For small time scales (delays), a good fit to the distributions of stock returns is obtained with q-Gaussian distributions, which can be derived either from Tsallis statistics or superstatistics. These distributions are symmetric. However, as the time lag increases, the distributions become increasingly non-symmetric. In this work, we address this problem by considering the data distribution as a linear combination of two independent normalized distributions - one for negative returns and one for positive returns. Each of these two independent distributions are half q-Gaussians with different non-extensivity parameter q and temperature parameter beta. Using this model, we investigate the behavior of stock market returns over time scales from 1 to 80 days. The data covers both the .com bubble and the 2008 crash periods. These investigations show that for all the time lags, the fits to the data distributions are better using asymmetric distributions than symmetric q-Gaussian distributions. The behaviors of the q parameter are quite different for positive and negative returns. For positive returns, q approaches a constant value of 1 after a certain lag, indicating the distributions have reached equilibrium. On the other hand, for negative returns, the q values do not reach a stationary value over the time scales studied. In the present model, the markets show a transition from normal to superdiffusive behavior (a possible phase transition) during the 2008 crash period. Such behavior is not observed with a symmetric q-Gaussian distribution model with q independent of time lag.

Banking Regulations - Understanding the Dodd-Frank Act and the Basel Accord
Caulker, Solomon
Regulators of financial institutions in most parts of the globe are making impressive achievement in terms of regulating the behavior of banks on the level of risk they can take in making investment decisions. Professionals in the finance industry have made a huge impact in trying to regulate these too-big-to-fail banks by drawing close lens in their lending activities. Aside from the reserve requirements of banks, there is also a capital requirement that caught the eyes of the Basel accord. This accord is extended from basel1 to basel2 and basel3. It came into existence as a result of the financial crisis in 2007. This crisis exposes a significant number of flaws in the financial system.Before this crisis, banks did not want to hold the excess reserve and so there was hardly any excess reserve in most banks. As a result of this, the money market multiplier exemplifies and works quite well since the amount of reserve was just around 10% to 15% of transactions in most countries. Apart from the capital requirement they now hold up to 25% of liquid assets as reserve requirement which is included in the Basel three accords, which is the recent regulatory document of the Basel accord. The Basel accord required banks to hold capital as a fraction of their risk-weighted assets. This initially created disturbances in the United States and the G20 countries because the Basel accord is similar to credit rating in many countries. This credit rating was abolished by the Dodd-Frank act of 2010 and so most governments especially the United States were no longer making use of regulations related to credit rating.Banks are required by the Basel accord to put a system in place that will regulate their loan facilities before they face a situation of negative capital. It is captured in this paper that the Basel accord will cut down on asymmetric information, externalities, and market power to avoid market failure. The off-balance sheet items are also taken into consideration by the Basel accord to reduce the high level of bank risk.

Black-box model risk in finance
Samuel N. Cohen,Derek Snow,Lukasz Szpruch

Machine learning models are increasingly used in a wide variety of financial settings. The difficulty of understanding the inner workings of these systems, combined with their wide applicability, has the potential to lead to significant new risks for users; these risks need to be understood and quantified. In this sub-chapter, we will focus on a well studied application of machine learning techniques, to pricing and hedging of financial options. Our aim will be to highlight the various sources of risk that the introduction of machine learning emphasises or de-emphasises, and the possible risk mitigation and management strategies that are available.

Can COVID-19 Solve The Equity Premium Puzzle?
Chibane, Messaoud
We propose a new methodology for estimating rare disaster event models where we only use U.S. data as an alternative to the ubiquitous Barro and Ursúa's (2008, 2012) international data set. Using a maximum likelihood approach, we show that the 2020 COVID crisis unambiguously reveals the presence and significance of rare disasters in consumption dynamics. Using our estimated parameters and recursive Epstein-Zin preferences, our approach is able to solve the risk-free rate and equity premium puzzles without resorting to international data in estimating the model nor using the ambiguity aversion channel in agent's preferences. Our results show that the severity of disasters is vastly underestimated and that more than 200 years of consumption data would be necessary to get an accurate estimate.

Diversifier or More? Hedge and Safe Haven Properties of Green Bonds During COVID-19
Arif, Muhammad,Naeem, Muhammad Abubakr,Farid, Saqib,Nepal, Rabindra,Jamasb, Tooraj
Against the backdrop of the Covid-19 pandemic, this study explores the hedging and safe-haven potential of green bonds for conventional equity, fixed income, commodity, and forex investments. We use the cross-quantilogram approach that provides a better understanding of the dynamic relationship between assets under different market conditions. Our full sample results show that the green bond index could serve as a diversifier asset for medium- and long-term equity investors. Besides, it can also serve as a hedging and safe haven instrument for currency and commodity investments. Moreover, the sub-sample analysis of the pandemic crisis period shows a heightened short- and medium-term lead-lag association between the green bond index and conventional investment returns. However, the green bond index emerges as a significant hedging and safe-haven asset for the long-term investors of conventional financial assets. Our results offer insights for long-term investors whose portfolios comprise conventional assets such as equities, commodities, forex, and fixed income securities. Further, our findings reveal the potential role that the green bond investments could play in global financial recovery efforts without compromising the low-carbon transition targets.

Do Retail Traders Destabilize Financial Markets? An Investigation Surrounding the COVID-19 Pandemic
Baig, Ahmed S.,Blau, Benjamin M.,Butt, Hassan A.,Yasin, Awaid
Economic theory suggests that speculative trading can lead to instability in financial markets. Using a novel dataset on retail trading activity in the US, this study extends the literature and investigates the impact of retail (speculative) trading on the volatility of the financial markets with a focus on the COVID-19 pandemic. Our tests are based on the retail trading data obtained from the discount brokerage Robinhood, a pioneer of commission free trading in the US, supplemented with data on odd lot trading obtained from the TAQ database. Using a series of econometric methods, we document a causal negative impact of speculative trading on the stability of the financial markets that was particularly enhanced during the pandemic. Our results are robust to a variety of time-series and panel tests, various multivariate estimation methodologies, corrections for endogeneity using quasi-natural experiments in a difference-in-difference setting, and the use of instrumental variable type regressions.

Good speciation and endogenous business cycles in a constraint satisfaction macroeconomic model
Dhruv Sharma,Jean-Philippe Bouchaud,Marco Tarzia,Francesco Zamponi

We introduce a prototype agent-based model of the macroeconomy, with budgetary constraints at its core. The model is related to a class of constraint satisfaction problems (CSPs), which has been thoroughly investigated in computer science. The CSP paradigm allows us to propose an alternative price-setting mechanism: given agents' preferences and budgets, what set of prices satisfies the maximum number of agents? Such an approach permits the coupling of production and output within the economy to the allowed level of debt in a simplified framework. Within our model, we identify three different regimes upon varying the amount of debt that each agent can accumulate before defaulting. In presence of a very loose constraint on debt, endogenous crises leading to waves of synchronized bankruptcies are present. In the opposite regime of very tight debt constraining, the bankruptcy rate is extremely high and the economy remains structure-less. In an intermediate regime, the economy is stable with very low bankruptcy rate and no aggregate-level crises. This third regime displays a rich phenomenology:the system spontaneously and dynamically self-organizes in a set of cheap and expensive goods (i.e. some kind of "speciation"), with switches triggered by random fluctuations and feedback loops. Our analysis confirms the central role that debt levels play in the stability of the economy. More generally, our model shows that constraints at the individual scale can generate highly complex patterns at the aggregate level.

How Much Insider Trading Really Happens in Stock Markets?
Patel, Vinay,Putniņš, Tālis J.
We estimate that the actual prevalence of illegal insider trading is at least four times greater than the number of prosecutions. Using novel empirical methods that explicitly account for the incomplete and non-random detection and hand-collected data of all US prosecuted insider trading cases, we estimate that insider trading occurs in one in five mergers and acquisition events and in one in 20 earnings announcements. Key drivers of the decision to engage in illegal insider trading include stock liquidity, the value of the inside information, and the number of people in possession of the information. Detection and prosecution are more likely when there are abnormal trading patterns and more regulatory resourcing.

Insider Trading and the Public Enforcement of Private Prohibitions: Some Complications in Enforcing Simple Rules for a Complex World
Miller, Robert T.
Accepting Epstein’s argument that firms wishing to allow their employees to insider trade should be permitted to do so, this article shows that there is still a crucial role for government in regulating insider trading. In particular, allowing employees to profit by insider trading is a form of employee compensation that, in contradistinction from conventional forms of equity compensation, results in unknowable and effectively unlimited costs to the company. Since providing employee compensation in this form causes the company to lose control of its compensation expense, even if insider trading were legal, virtually every company would rely on conventional forms of employee compensation and prohibit its employees from insider trading. But, pace Epstein, companies lack the means to detect insider trading by their employees, and even when they do catch employees insider trading, companies can impose only mild contractual sanctions, generally not exceeding disgorgement of profits and dismissal. As a result, although an efficient agreement between a company and its employee would prohibit the employee from insider trading, this prohibition cannot be effectively enforced by the company. Government, with its usual law enforcement powers, is better able to detect insider trading and can impose more severe sanctions on violators, including criminal penalties. Government should thus enforce a ban on insider trading in those instances, which will be virtually all instances, in which a company prohibits its employees from insider trading. The efficient solution is thus a hybrid system of private prohibition and public enforcement. Such a system is not unusual but the norm. Employers prohibit employees from embezzling their money and stealing their property, and employees are subject to contractual sanctions and dismissal for violating these prohibitions, but we still need statutes against theft to generate an optimal level of deterrence. This is all the more true when the employee misappropriates information, which is much harder to detect than a theft of money or property.

Insights from Company Experts in Valuing Complex Estimates: The Other Side of the Story!
Kjellevold, Kyrre,Eilifsen, Aasmund,Messier, Jr., William F.
Management frequently uses company experts to provide fair value measurements (FVMs) of complex estimates. We conduct detailed interviews with Norwegian company experts who possess expertise in financial instruments, investment property, oil & gas, and shipping; and audit partners to investigate issues derived from agency theory and the monitoring activities of company experts. Our results show the company experts’ side of the story. First, company experts have incentives to build and maintain their reputation, are aware of the impact of conflicts-of-interest on reputation, and that reputation plays a role in their reappointment. Second, company experts face management pressure and several influence tactics are documented. Third, management strategically uses multiple company experts for FVMs. Fourth, some types of company experts strategically guard their valuation models and proprietary information. Fifth, the company experts confirmed that auditors focus on individual assumptions and fail to see the “big picture.” Finally, the company experts report limited interaction with the audit team. These findings support our theoretical framework and inform researchers, regulators, and practitioners about the role company experts play in the fair value estimate process.

Know Thyself: Free Credit Reports and The Retail Mortgage Market
Kumar, Amit
Under imprecise creditworthiness information, borrowers may take erroneous credit decisions. Credit reports---which record one’s creditworthiness---became free in entire US in 2005, while they already had been free in seven states. Exploiting this in a difference-in-differences setting, this paper shows that cheaper credit reports to consumers improved mortgage market outcomes. The applications, approvals and borrowing in high-creditworthy areas increased, and defaults and subprime population fraction decreased. Also, first-time homeowner proportion increased, and lenders’ financial performance improved. Additional findings, including increased interest rates, suggest a demand-driven improvement in the applicant pool, as consumers receive precise creditworthiness signal from their reports.

Liquidation, Leverage and Optimal Margin in Bitcoin Futures Markets
Zhiyong Cheng,Jun Deng,Tianyi Wang,Mei Yu

Using the generalized extreme value theory to characterize tail distributions, we address liquidation, leverage, and optimal margins for bitcoin long and short futures positions. The empirical analysis of perpetual bitcoin futures on BitMEX shows that (1) daily forced liquidations to out- standing futures are substantial at 3.51%, and 1.89% for long and short; (2) investors got forced liquidation do trade aggressively with average leverage of 60X; and (3) exchanges should elevate current 1% margin requirement to 33% (3X leverage) for long and 20% (5X leverage) for short to reduce the daily margin call probability to 1%. Our results further suggest normality assumption on return significantly underestimates optimal margins. Policy implications are also discussed.

Lowest-cost virus suppression
Jacob Janssen,Yaneer Bar-Yam

Analysis of policies for managing epidemics require simultaneously an economic and epidemiological perspective. We adopt a cost-of-policy framework to model both the virus spread and the cost of handling the pandemic. Because it is harder and more costly to fight the pandemic when the circulation is higher, we find that the optimal policy is to go to zero or near-zero case numbers. Without imported cases, if a region is willing to implement measures to prevent spread at one level in number of cases, it must also be willing to prevent the spread with at a lower level, since it will be cheaper to do so and has only positive other effects. With imported cases, if a region is not coordinating with other regions, we show the cheapest policy is continually low but nonzero cases due to decreasing cost of halting imported cases. When it is coordinating, zero is cost-optimal. Our analysis indicates that within Europe cooperation targeting a reduction of both within country transmission, and between country importation risk, should help achieve lower transmission and reduced costs.

Models, Markets, and the Forecasting of Elections
Rajiv Sethi,Julie Seager,Emily Cai,Daniel M. Benjamin,Fred Morstatter

We examine probabilistic forecasts for battleground states in the 2020 US presidential election, using daily data from two sources over seven months: a model published by The Economist, and prices from the PredictIt exchange. We find systematic differences in accuracy over time, with markets performing better several months before the election, and the model performing better as the election approached. A simple average of the two forecasts performs better than either one of them overall, even though no average can outperform both component forecasts for any given state-date pair. This effect arises because the model and the market make different kinds of errors in different states: the model was confidently wrong in some cases, while the market was excessively uncertain in others. We conclude that there is value in using hybrid forecasting methods, and propose a market design that incorporates model forecasts via a trading bot to generate synthetic predictions. We also propose and conduct a profitability test that can be used as a novel criterion for the evaluation of forecasting performance.

Network Based Evidence of the Financial Impact of COVID-19 Pandemic
Ahelegbey, Daniel Felix,Cerchiello, Paola,Scaramozzino, Roberta
How much the largest worldwide companies, belonging to different sectors of the economy, are suffering from the pandemic? Are economic relations among them changing? In this paper, we address such issues by analysing the top 50 S\&P companies by means of market and textual data. Our work proposes a network analysis model that combines such two types of information to highlight the connections among companies with the purpose of investigating the relationships before and during the pandemic crisis. In doing so, we leverage a large amount of textual data through the employment of a sentiment score which is coupled with standard market data. Our results show that the COVID-19 pandemic has largely affected the US productive system, however differently sector by sector and with more impact during the second wave compared to the first.

Portfolio Construction Using Stratified Models
Jonathan Tuck,Shane Barratt,Stephen Boyd

In this paper we develop models of asset return mean and covariance that depend on some observable market conditions, and use these to construct a trading policy that depends on these conditions, and the current portfolio holdings. After discretizing the market conditions, we fit Laplacian regularized stratified models for the return mean and covariance. These models have a different mean and covariance for each market condition, but are regularized so that nearby market conditions have similar models. This technique allows us to fit models for market conditions that have not occurred in the training data, by borrowing strength from nearby market conditions for which we do have data. These models are combined with a Markowitz-inspired optimization method to yield a trading policy that is based on market conditions. We illustrate our method on a small universe of 18 ETFs, using three well known and publicly available market variables to construct 1000 market conditions, and show that it performs well out of sample. The method, however, is general, and scales to much larger problems, that presumably would use proprietary data sources and forecasts along with publicly available data.

Some results on the risk capital allocation rule induced by the Conditional Tail Expectation risk measure
Nawaf Mohammed,Edward Furman,Jianxi Su

Risk capital allocations (RCAs) are an important tool in quantitative risk management, where they are utilized to, e.g., gauge the profitability of distinct business units, determine the price of a new product, and conduct the marginal economic capital analysis. Nevertheless, the notion of RCA has been living in the shadow of another, closely related notion, of risk measure (RM) in the sense that the latter notion often shapes the fashion in which the former notion is implemented. In fact, as the majority of the RCAs known nowadays are induced by RMs, the popularity of the two are apparently very much correlated. As a result, it is the RCA that is induced by the Conditional Tail Expectation (CTE) RM that has arguably prevailed in scholarly literature and applications. Admittedly, the CTE RM is a sound mathematical object and an important regulatory RM, but its appropriateness is controversial in, e.g., profitability analysis and pricing. In this paper, we address the question as to whether or not the RCA induced by the CTE RM may concur with alternatives that arise from the context of profit maximization. More specifically, we provide exhaustive description of all those probabilistic model settings, in which the mathematical and regulatory CTE RM may also reflect the risk perception of a profit-maximizing insurer.

Study of State-Owned Enterprises (SOEs) Profitability in Indonesia 2012-2016 Period
Muin, Muhamad Fathul,Ridwan, Jumadi,Wardini, Amalia Kusuma
One of the purposes of the establishment of SOEs is to become a source of funding for the state. But unfortunately, the losses and potential bankruptcy is still a business challenge to date. Therefore, the aims of this research to analyze the SOEs’ financial performance and the factors that affected profitability. The analysis method used is panel data regression involving 118 financial data companies in the year of 2012-2016. The variables used consisted of return on assets (ROA), total asset growth (TAG), current ratio (CR), total assets turnover (TATO), and debt to equity ratio (DER). After eliminating the outlier data and use other statistical tests, a fixed-model effect (FEM) was obtained. Based on the analysis result, the effect of TAG, CR, and TATO is positive and significant on the ROA. Meanwhile, the effect of the DER is not significant on ROA. This model is able to explain the variation of the dependent variable of 92,40 percent.

The Financial Restitution Gap in Consumer Finance: Insights from Complaints Filed with the CFPB
Haendler, Charlotte,Heimer, Rawley
Consumers seek restitution for disputed financial services by filing complaints with the Consumer Financial Protection Bureau (CFPB). We find that filings from low-socioeconomic (i.e., low-income and African American) zip codes were 30% less likely to be resolved with the consumer receiving financial restitution. At the same time, low- and high-socioeconomic zip codes submitted an equal share of the CFPB complaints. The socioeconomic gap in financial restitution was scarcely present under the Obama administration, but grew substantially under the Trump administration. We attribute the change in financial restitution under different political regimes to companies anticipating a more industry-friendly CFPB, as well as to the more industry-friendly leadership of the CFPB achieving less financial restitution for low-socioeconomic filers. The financial restitution gap cannot be explained by differences in product usage nor the quality of complaints, which we measure using textual analysis.

The Privatization Effects on Iran Insurance Industry
Karimi, Mohammad,cheshomi, ali,Hassannezhad Kashani, Behzad
Two methods of privatization through ownership transfer and privatization from below are more proper than other ones. The privatization program in Iran insurance industry is performed through privatization from below initiated from 2000 and proceeded in recent years by ownership transfer according to general policies of Iran Law. This paper shows how privatization from below is effective more than ownership privatization in competition extension in insurance industry and spread of its supporting businesses. This method have had more effects on insurance industry by extending insurance industry practices, leading to differentiation in insurance products, improving public firms' performance and extending insurance relevant businesses.

The Sensitivity of Risk Premiums to the Elasticity of Inter-Temporal Substitution
Wu, Zhiting
I incorporate the recursive utility into Pagel (2016)'s reference-dependent preference and study their aggregate implications in a consumption-based asset pricing model. In the case of recursive utility, the proposed model reproduces crucial asset pricing moments and time-varying risk premiums with a simple IID process for consumption growth. Second, the proposed model consistently predicts that the agent prefers a late resolution of uncertainty in both time-separable and recursive utility. My additional finding is that intertemporal substitution elasticity is more sensitive to asset prices given the recursive preference. Finally, the introduction of sluggish-updating can improve model performances.

Unconventional Monetary Policy and the Search for Yield
Kandrac, John,Kokas, Sotirios,Kontonikas, Alexandros
We use U.S. syndicated loan market data to examine how banks responded to the unprecedented injection of reserves by the Fed over several rounds of quantitative easing (QE). We show that higher reserves boost bank lending. To establish a causal interpretation for this finding, we construct a novel instrument for the bank-level exposure to QE by using confidential data on daily bank reserves. Next, we identify a mechanism that can explain this link. We show that the connection between banks' reserves and lending volume depends upon the net return that banks enjoy on reserve balances. Our findings demonstrate that the search for yield component of the risk taking channel â€" wherein banks increase risk-taking to achieve nominal profitability targets during periods of low interest rates â€" is also a relevant consideration for policymakers during massive reserve injections.

Var and Market Value of Fintech Companies: An Analysis and Evidence From Global Data
Liew, Chee Yoong,Najaf, Khakan,Schinckus, Christophe
Purpose â€" This study aims at determining the portfolio value at risk (VAR) and market value of Fintech firms and compare it with their counterparts.Design/methodology/approach â€" By using on a dataset from 46 countries between 2009 and 2018, the authors use five measures of VaR to investigate their empirical dynamics in relation with the market value of Fintech and non-Fintech companies.Findings â€" The empirical results indicate that Fintech firms’ portfolios have a higher financial risk and a higher market value in comparison to non-fintech firms’ portfolios. Furthermore, the authors also report that the Fintech firm portfolios experience more financial risk regardless of the holding period as long-term (one year) or short-term (quarter).Research limitations/implications â€" There are some limitations in this research. This research does not segregate Fintech firms into their different types of services, such as direct financial investment services, loan provision services, insurance services (InsurTech), etc. The authors only aggregate the Fintech firms by country and region. Future research may consider analysing Fintech firms by differentiating the kind of financial services they offerPractical implications â€" Given the importance of their market value, the results imply that Fintech companies might contribute significantly to financial fluctuations in case of large variations of the market. In terms of policy recommendation, this observation requires a particular attention from the regulatory bodies who need to find the best economic balance between promoting innovation/financial technology and regulating the Fintech companies.Originality/value â€" This paper is the first study clarifying the relation of financial risk and market value for the Fintech firms, using the large enough database to obtain significant results. This article implies that Fintech companies require a robust risk management framework.

View about consumption tax and grandchildren
Eiji Yamamura

In Japan, the increase in the consumption tax rate, a measure of balanced public finance, reduces the inequality of fiscal burden between the present and future generations. This study estimates the effect of grandchildren on an older person's view of consumption tax, using independently collected data. The results show that having grandchildren is positively associated with supporting an increase in consumption tax. Further, this association is observed strongly between granddaughters and grandparents. However, the association between grandsons and grandparents depends on the sub-sample. This implies that people of the old generation are likely to accept the tax burden to reduce the burden on their grandchildren, especially granddaughters. In other words, grandparents show intergenerational altruism.

Wavelet Denoised-ResNet CNN and LightGBM Method to Predict Forex Rate of Change
Yiqi Zhao,Matloob Khushi

Foreign Exchange (Forex) is the largest financial market in the world. The daily trading volume of the Forex market is much higher than that of stock and futures markets. Therefore, it is of great significance for investors to establish a foreign exchange forecast model. In this paper, we propose a Wavelet Denoised-ResNet with LightGBM model to predict the rate of change of Forex price after five time intervals to allow enough time to execute trades. All the prices are denoised by wavelet transform, and a matrix of 30 time intervals is formed by calculating technical indicators. Image features are obtained by feeding the maxtrix into a ResNet. Finally, the technical indicators and image features are fed to LightGBM. Our experiments on 5-minutes USDJPY demonstrate that the model outperforms baseline modles with MAE: 0.240977x10EXP-3 MSE: 0.156x10EXP-6 and RMSE: 0.395185x10EXP-3. An accurate price prediction after 25 minutes in future provides a window of opportunity for hedge funds algorithm trading. The code is available from

Will Loyalty Shares Do Much for Corporate Short-Termism?
Roe, Mark J.,Cenzi Venezze, Federico
Stock-market short-termismâ€"stemming from rapid trading and activists looking for quick cashâ€"is, a widespread view has it, hurting the American economy. Because stock markets will not support corporate long-term planning, the thinking goes, companies fail to invest enough, do not do enough research and development, and buy back so much of their stock that their coffers are depleted of cash for their future. This widespread view has induced proposals for remedy. One major proposal is for corporate “loyalty shares,” whereby stockholders who own their stock for longer periods would get more voting power than those who trade their stock quickly. That voting boost would, it’s hoped, support stability and sound long-term planning. Venture capitalists have already obtained the go-ahead from the Securities and Exchange Commission to found the “Long-Term Stock-Exchange,” as it is calledâ€"whose centerpiece has been loyalty shares and their concomitant voting boost for companies on the new exchange. In this article, we show why loyalty shares promoters’ thinking is overly optimistic. Facilitating insider control will be loyalty shares’ dominant motive and effect. Long-term thinking, planning, and investing will be weaker motivations and effects. Indeed, loyalty shares will at times undermine long-term planning at companies that use them.Loyalty share voting boosts would shift voting power in those U.S. public companies that adopt them, but they will not shift voting power toward shareholders most likely to promote the long-term. Instead, we should expect loyalty shares to empower conflicted corporate players who seek not more corporate focus on the long-term but to better protect themselves and their corporate positions. Controller-insider self-interest will dominate their motivation, not fighting short-termism, because insiders have self-interested reasons to lock in control and shut down outsiders, even if doing so fails to improve corporate time horizons. Policymakers with a bona fide long-term vision will find themselves frustrated by the outcome. Existing data from Europe, where loyalty shares are more extensively used thus far than in the United States, supports this structural analysis. Control motivations dominate; long-term motivations are pale or absent from the on-the-ground practice. Other reasonsâ€"as yet undiscussed as far as we can tellâ€"may well justify opening corporate law to loyalty share programs. We introduce to the loyalty share analysis the ex ante value to the entrepreneur of retaining controlâ€"i.e., loyalty shares can help to motivate founders and thereby induce new entry, new start-ups, and new, original entrepreneurial activity. Weighing the value of continued control in fostering start-ups and original entrepreneurial activity against its later costs is not easy and it is not obvious which weighs more but, if there is economy-wide value to loyalty shares, that motivational value is where it is likely to reside. For short-termism, policymakers should be skeptical that promoting sound corporate long-termism will be a major result of facilitating loyalty shares in the American corporation.