Trading Agent Research Articles

Optimal Trading with Differing Trade Signals

We consider the problem of maximizing portfolio value when an agent has a subjective view on asset value which differs from the traded market price. The agent's trades will have a price impact which affect the price at which the asset is traded. In addition to the agent's trades affecting the market price, the agent may change his view on the asset's value if its difference from the market price persists. We also consider a situation of several agents interacting and trading simultaneously when they have a subjective view on the asset value. Two cases of the subjective views of agents are considered, one in which they all share the same information, and one in which they all have an individual signal correlated with price innovations. To study the large agent problem we take a mean-field game approach which remains tractable. After classifying the mean-field equilibrium we compute the cross-sectional distribution of agents' inventories and the dependence of price distribution on the amount of shared information among the agents.

Coordination of Purchasing and Bidding Activities Across Markets

In both consumer purchasing and industrial procurement, combinatorial interdependencies among the items to be purchased are commonplace. E-commerce compounds the problem by providing more opportunities for switching suppliers at low costs, but also potentially eases the problem by enabling automated market decision-making systems, commonly referred to as trading agents, to make purchasing decisions in an integrated manner across markets. Most of the existing research related to trading agents assumes that there exists a combinatorial market mechanism in which buyers (or sellers) can bid (or sell) service or merchant bundles. Today's prevailing e-commerce practice, however, does not support this assumption in general and thus limits the practical applicability of these approaches. We are investigating a new approach to deal with the combinatorial interdependency challenges for online markets. This approach relies on existing commercial online market institutions such as posted-price markets and various online auctions that sell single items. It uses trading agents to coordinate a buyer's purchasing and bidding activities across multiple online markets simultaneously to achieve the best overall procurement effectiveness. This paper presents two sets of models related to this approach. The first set of models formalizes optimal purchasing decisions across posted-price markets with fixed transaction costs. Flat shipping costs, a common e-tailing practice, are captured in these models. We observe that making optimal purchasing decisions in this context is NP-hard in the strong sense and suggest several efficient computational methods based on discrete location theory. The second set of models is concerned with the coordination of bidding activities across multiple online auctions. We study the underlying coordination problem for a collection of first or second-price sealed-bid auctions and derive the optimal coordination and bidding policies.

Impact Analysis of Financial Regulation on Multi-Asset Markets Using Artificial Market Simulations

In this study, we assessed the impact of capital adequacy ratio (CAR) regulation in the Basel regulatory framework. This regulation was established to make the banking network robust. However, a previous work argued that CAR regulation has a destabilization effect on financial markets. To assess impacts such as destabilizing effects, we conducted simulations of an artificial market, one of the computer simulations imitating real financial markets. In the simulation, we proposed and used a new model with continuous double auction markets, stylized trading agents, and two kinds of portfolio trading agents. Both portfolio trading agents had trading strategies incorporating Markowitz’s portfolio optimization. Additionally, one type of portfolio trading agent was under regulation. From the simulations, we found that portfolio optimization as each trader’s strategy stabilizes markets, and CAR regulation destabilizes markets in various aspects. These results show that CAR regulation can have negative effects on asset markets. As future work, we should confirm these effects empirically and consider how to balance between both positive and negative aspects of CAR regulation.

Adaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach

In recent years, considerable efforts have been devoted to developing AI techniques for finance research and applications. For instance, AI techniques (e.g., machine learning) can help traders in quantitative trading (QT) by automating two tasks: market condition recognition and trading strategies execution. However, existing methods in QT face challenges such as representing noisy high-frequent financial data and finding the balance between exploration and exploitation of the trading agent with AI techniques. To address the challenges, we propose an adaptive trading model, namely iRDPG, to automatically develop QT strategies by an intelligent trading agent. Our model is enhanced by deep reinforcement learning (DRL) and imitation learning techniques. Specifically, considering the noisy financial data, we formulate the QT process as a Partially Observable Markov Decision Process (POMDP). Also, we introduce imitation learning to leverage classical trading strategies useful to balance between exploration and exploitation. For better simulation, we train our trading agent in the real financial market using minute-frequent data. Experimental results demonstrate that our model can extract robust market features and be adaptive in different markets.

The 2020 Power Trading Agent Competition

This is the specification for the Power Trading Agent Competition for 2020 (Power TAC 2020). Power TAC is a competitive simulation that models a “liberalized” retail electrical energy market, where competing business entities or “brokers” offer energy services to customers through tariff contracts, and must then serve those customers by trading in a wholesale market. Brokers are challenged to maximize their profits by buying and selling energy in the wholesale and retail markets, subject to fixed costs and constraints; the winner of an individual “game” is the broker with the highest bank balance at the end of a simulation run. Costs include fees for publication and withdrawal of tariffs, for rectifying supply-demand imbalances, for contributions to peak demand, and for customer connections. The simulation environment models a wholesale market, a regulated distribution utility, and a population of energy customers, situated in a real location on Earth during a specific period for which weather data is available. The wholesale market is a relatively simple call market, similar to many existing wholesale electric power markets, such as Nord Pool in Scandinavia or FERC markets in North America, but unlike the FERC markets we are modeling a single region, and therefore we approximate the effects of locational-marginal pricing through manipulation of the wholesale supply curve. Customer models include households, electric vehicles, and a variety of commercial and industrial entities, many of whom have production capacity such as solar panels or wind turbines. All have “real-time” metering to support allocation of their hourly supply and demand to their subscribed brokers, and all are approximate utility maximizers with respect to tariff selection, although the factors making up their utility functions may include aversion to change and complexity that can retard uptake of marginally better tariff offers. A distribution utility models the regulated natural monopoly that owns the regional distribution network, and is responsible for maintenance of its infrastructure. Real-time balancing of supply and demand is managed by a market-based mechanism that uses economic incentives to encourage brokers to achieve balance within their portfolios of tariff subscribers and wholesale market positions, in the face of stochastic customer behaviors and weather-dependent renewable energy sources. Changes for 2020 are focused on stability and on making customer evaluation of regulation rates more realistic, and are highlighted by change bars in the margins. See Section 4.1.1 for details.

ЕКОЛОГІЧНИЙ МАРКЕТИНГ У ПОВОДЖЕННІ ІЗ ПОБУТОВИМИ ВІДХОДАМИ ДЛЯ ЗАБЕЗПЕЧЕННЯ СТАЛОГО РОЗВИТКУ УКРАЇНИ

Solution to the problem of recycling and reducing the amount of household and other types of waste, their subsequent use as secondary raw materials, prevention of formation plays an important role in ensuring the sustainable development of the country. This problem is of particular importance in Ukraine, as the amount of waste here is constantly increasing and the area on which it is located is growing, there is a low level of recycling, landfills do not meet the requirements of environmental safety and pose a significant threat to the environment and human health. The solution to this problem is possible using the conception of ecological marketing by product manufacturers as well as trade agents and state authorities. The goal of this paper is to justify the means of ecological marketing, which are directed to the management of using of household and other types of waste as well as reducing their amount. It was found that ecological consciousness and habits of the population have significant impact to providing wastes separation and their recycling. It was detected that they are dependent on price for waste collection. Effective state-level communicative policy also can stimulate population to proper behavior related to household waste, reducing their amount and separation. The policy may include educational programs implementation through conducting ecology classes at schools and other educational institutions, implementation of ecological measures as events by municipal authorities, that will allow to engage young generation to solution of ecological problems, construct their ecological consciousness. Simultaneously engaging civil and religion organizations that can impact to behavior is important for constructing more responsible attitude of elderly people to solution of ecological problems. Domestic enterprises can play significant role in preventing of wastes producing. That will provide a bunch of benefits for society, customers, and enterprises. Recommended measures for ecological marketing were proposed in the article for manufacturers and trade agents for preventing of household and other types of waste. REFERENCES:1. Bublyk M.I. Ekolohichnyi marketynh yak instrument mekhanizmu rozvytku sotsio-ekoloho-ekonomichnoi systemy. Visnyk Natsionalnoho universytetu "Lvivska politekhnika". Seriia "Lohistyka". 2011. No. 706. P. 202-207 [in Ukrainian].2. Shaporenko O.I. Ekolohichnyi marketynh yak zaporuka yakosti zhyttia: kontseptsii, stratehiia, rynok. Derzhavne upravlinnia: udoskonalennia ta rozvytok. 2019. No. 2. https://doi.org/10.32702/2307-2156-2019.2.6 [in Ukrainian].3. Vladymyrova M.S. Formuvannia ekolohichnoho marketynhu na pidpryiemstvi. Molodyi vchenyi. 2016. No. 4 (31). P. 35-38 [in Ukrainian].4. Maliei O.V. Udoskonalennia ekonomichnoho instrumentariiu upravlinnia u sferi povodzhennia z tverdymy pobutovymy vidkhodamy na rehionalnomu rivni. Efektyvna ekonomika. 2013. No. 12. URL: http://www.economy.nayka.com.ua/?op=1&z=2567 [in Ukrainian].5. Boronos V.H., Shkarupa O.V., Konovalov M.H. Ekolohichna modernizatsiia systemy upravlinnia povodzhennia z tverdymy pobutovymy vidkhodamy v Ukraini na osnovi dosvidu YeS ta Norvehii. Marketynh i menedzhment innovatsii. 2016. No. 2. P. 222-234 [in Ukrainian].6. Luca F.A., Ioan C.A. Іmplementation of green marketing in the analysis of municipal waste produced in Romania, correlated with environmental policy management. Environmental Engineering and Management. 2014. Vol. 13. № 12. Р. 3131-3142. URL: https://pdfs.semanticscholar.org/b1a5/29172af6693c4d40908f5cbaea7f8cab2765.pdf7. So W., Chow C., Lee J. (Eds.) Environmental Sustainability and Education for Waste Management. URL: https://www.springer.com/gp/book/97898113917298. Navkolyshnie pryrodne seredovyshche. Derzhavna sluzhba statystyky Ukrainy. URL: http://www.ukrstat.gov.ua [in Ukrainian].9. Environment. Eurostat. URL: https://ec.europa.eu/eurostat/data/database10. Pobutovi vidkhody v Ukraini ta YeS: obsiahy ta stan povodzhennia u 2017 rotsi. Ekonomichnyi dyskusiinyi klub. URL: http://edclub.com.ua/analityka/pobutovi-vidhody-v-ukrayini-ta-yes-obsyagy-ta-stan-povodzhennya-u-2017-roci [in Ukrainian].11. Tverdi pobutovi vidkhody v Ukraini: potentsial rozvytku. IFC. URL: https://www.ifc.org/wps/wcm/connect/504c5765-89d4-4be1-916e-ea27aa94feaf/22.+/.../pdf [in Ukrainian].12. Voitsikhovska A., Kravchenko O., Melen-Zabramna O., Pankevych M. Krashchi yevropeiski praktyky upravlinnia vidkhodamy: posibnyk. Za zah. red. O. Kravchenko. Lviv, 2019. 64 p. [in Ukrainian].13. Z travnia diiut novi pravyla povodzhennia z pobutovymy vidkhodamy. VHO "Spilka vlasnykiv zhytla Ukrainy". URL: https://spilka.pro/z-travnya-diyut-novi-pravyla-povodzhennya-z-pobutovymy-vidhodamy [in Ukrainian].14. Vidpovidalnyi rozvytok. Ofitsiinyi sait PrAT "Karlsberh Ukraina". URL: https://carlsbergukraine.com/#v-dpov-dalniy-rozvitok [in Ukrainian].15. Kuzo N.Ie., Kosar N.S., Dudnik B.E. Korporatyvna sotsialna vidpovidalnist u formuvanni pozytyvnoho imidzhu kondyterskoho pidpryiemstva na rynku. Infrastruktura rynku. 2019. Iss. 27. P. 174-181. URL: http://www.marketinfr.od.ua/journals/2019/27_2019_ukr/29.pdf [in Ukrainian].16. Tserkva i ekolohiia. Relihiino-informatsiina sluzhba Ukrainy. URL: https://risu.org.ua/ua/index/all_news/community/ecology/ [in Ukrainian].

Hedging nontradable risks with transaction costs and price impact

AbstractA risk‐averse agent hedges her exposure to a nontradable risk factor U using a correlated traded asset S and accounts for the impact of her trades on both factors. The effect of the agent's trades on U is referred to as cross‐impact. By solving the agent's stochastic control problem, we obtain a closed‐form expression for the optimal strategy when the agent holds a linear position in U. When the exposure to the nontradable risk factor is nonlinear, we provide an approximation to the optimal strategy in closed‐form, and prove that the value function is correctly approximated by this strategy when cross‐impact and risk‐aversion are small. We further prove that when is nonlinear, the approximate optimal strategy can be written in terms of the optimal strategy for a linear exposure with the size of the position changing dynamically according to the exposure's “Delta” under a particular probability measure.

Bubbles and Trading Frenzies: Evidence from the Art Market

The art market is subject to booms and busts in both prices and volume, which are difficult to reconcile with models where agents trade to consume. This paper shows that: (i) a high trading volume coincides with higher prices and more speculative trades, (ii) a high volume predicts negative returns, especially in the most volatile art schools, (iii) a substantial increase in transaction costs decreases art prices and can destroy the return-volume relation, and (iv) short-term transactions underperform and are riskier than long-term transactions. The evidence is consistent with a resale option model of speculative trading where the impossibility to sell short embeds a bubble component in prices. This paper suggests that speculative trading can generate significant price bubbles, even when trading costs are huge.

Trading Saudi Stock Market Shares using Multivariate Recurrent Neural Network with a Long Short-term Memory Layer

This study tests the Saudi stock market weak form using the weak form of an efficient market hypothesis and proposes a recurrent neural network (RNN) to produce a trading signal. To predict the next-day trading signal of several shares in the Saudi stock market, we designed the RNN with a long short-term memory architecture. The network input comprises several time series features that contribute to the classification process. The proposed RNN output is fed to a trading agent that buys or sells shares based on the share current value, current available balance, and the current number of shares owned. To evaluate the proposed neural network, we used the historical oil price data of Brent crude oil in combination with other stock features (e.g., previous day (opening and closing price of the evaluated share). The results indicate that oil price variations affect the Saudi stock market. Furthermore, with 55% accuracy, the proposed RNN model produces the next-day trading signal. For the same period, the proposed RNN trading method achieves an investment gain of 23%, whereas the buy-and-hold method obtained 1.2%.

Stock Market Trading Agent Using On-Policy Reinforcement Learning Algorithms

Stock market has been a complex system which has been difficult to predict for humans, thereby, making the trading decisions difficult to take. It will be useful for traders if there is a model agent which can learn the stock market trends and suggest trading decisions which in turn maximizes the profits. Inorder to develop this agent we have formulated the problem as a Markov Decision Process (MDP) and created a stock trading environment which serves as a platform for this agent to trade the stocks. In this paper, we introduce a Reinforcement Learning based approach to develop a trading agent which performs trading actions on the environment and learns according to the rewards in terms of profit or loss it receives. We have applied different On-policy Reinforcement Learning Algorithms such as Vanilla Policy Gradient (VPG), Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) on the environment to obtain the profits while trading stocks for 3 companies viz. Apple, Microsoft and Nike. The performance of these algorithms in order to maximize the profits have been evaluated and the results and conclusions have been elaborated.

US Imperialism and Puerto Rican Needleworkers: Sovereignty, Citizenship, and Women's Labor in a Deep History of Neoliberal Trade

AbstractIn 1898, US occupation of Puerto Rico opened possibilities for experimentation with manufacturing, investment, tariffs, and citizenship because the Treaty of Paris did not address territorial incorporation. Imperial experimentation started immediately and continued through the liberal policies of the New Deal and World War II, consistently reproducing drastic exceptions. These exceptions were neither permanent nor complete, but the rearrangements of sovereignty and citizenship established Puerto Rico as a site of potential and persistent exemption. Puerto Rican needleworkers were central to the resulting colonial industrialization-not as dormant labor awaiting outside developmental forces but as skilled workers experienced in production. Following US occupation, continental trade agents and manufacturers noted the intricate needlework of Puerto Rican women and their employment in homes and small shops for contractors across the island. Their cooptation and adaptation of this contracting system led to the colonial industrialization, generating bureaucratic, financial, and legal infrastructure later used in Operation Bootstrap, a long-term economic plan devised in the 1940s and 1950s. Labor unions and aggrieved workers contested and resisted this colonial industrialization. They advocated their own proposals and pushed against US economic policies and insular business management. Throughout these fights, the asymmetrical power of the federal government and industrial capital allowed the colonial regime to assert US sovereignty while continually realigning exemptions and redefining citizenship for liberal economic objectives. Rather than representing a weakening of the nation-state, this strong interventionist approach provided scaffolding for Operation Bootstrap, which became a model for the neoliberal projects called export processing zones (EPZs).

“Angajawi”, or, On Being Muslim Nusantara: The Global Argument for Islam (ic) Nusantara

The article is an examination of practices, such as the transmission and movement of ideas and knowledge, by which Indonesian Islam or what is called Islam(ic) Nusantara comes into being as a distinct civilizational body, and then considers the ways in which these practices claim a place in a wider Muslim societies. “Angajawi” (being Muslim Nusantara) is a strategic term to convey these practices, while, at the same time, to look closely at the way they constitute the vitality and resilience of Islam(ic) Nusantara cultural riches among the citizens of Muslim world. The method followed in this article is firstly to track down the flow of ideas from Jawi or Nusantara as they were brought about by Indonesian agents of trade, knowledge and pilgrimage to the Holy Land since earlier centuries of the coming of Islam to Indonesia; and then, secondly, to draw our attention to the worldwide Muslim reception of these ideas as the creative energy and qualities of Indonesian Islam in dealing with the problems of humanity. Furthermore, the meaning of “Islam Nusantara” needs to be clarified so as to provide a clear comprehension of the globalized qualities or core ideals of “angajawi”. 
 
 Keywords: angajawi, Islam Nusantara, history of Islam, Indonesian Islam

Presídias dos terceiros do Carmo de Vila Rica: territorialidade e rede confraternal em Minas Gerais, 1744-1848

A pesquisa trata da configuração institucional da Ordem Terceira do Carmo da capital político-administrativa do território minerário, Vila Rica ou Ouro Preto, através das suas filiais, as presídias (presidências locais), cuja disseminação ultrapassou os limites da capitania/província de Minas Gerais, no interior brasileiro. As presídias forneceram à sede-matriz da Ordem Terceira rendimentos acrescidos (pagamentos, doações, concessões) que não eram acessíveis às irmandades reduzidas a uma jurisdição paroquial. As filiais da Ordem foram os dispositivos fundamentais de integração local dos associados (agentes do comércio ou emigrados) e da instituição da fraternidade, com papel destacado nas alianças de amizade e de parentesco. Essa associação religiosa de abrangência territorial, justaposta à teia de freguesias das Minas (matrizes e capelas), conformou uma elite político-econômica e as identidades dos agentes de poder (brancos, senhores, autoridades políticas, militares), contribuindo para forjar noções de pertencimento comunitário e de reconhecimento de grupo (conforme o estamento). Através da difusão das presídias, ademais, pode-se apreender o mercado dos bens simbólicos relacionados às práticas devocionais carmelitanas.

Optimal contracting in networks

We study optimal contracting between a firm selling a divisible good that exhibits positive externality and a group of agents in a social network. The extent of externality that each agent receives from the consumption of neighboring agents is privately held and is unknown to the firm. By explicitly characterizing the optimal multilateral contract, we demonstrate how inefficiency in an agent's trade propagates through the network and creates unequal and network-dependent downward distortion in other agents' trades. Furthermore, we describe bilateral contracts (non-linear pricing schemes) and characterize their explicit dependence on the network structure. We show that the firm will benefit from uncertainty in an agent's valuation of other agents' externality. We describe the profit gap between multilateral and bilateral contracts and analyze the consequences of the explicit dependence of the contracts on network structure. When the network is balanced in terms of homogeneity of agents' influence, network structure has no impact on the firm's profit for bilateral contracts. On the other hand, when the influences are heterogeneous with high dispersion (as in core-periphery networks) the restriction to bilateral contracts can result in profit losses that grow unbounded with the size of networks.

Metaorder limit prices in evaluating expected market impact and assessing execution service quality

The paper examines the bias introduced by metaorder limit prices when measuring quality of execution services on financial market. While evaluating the quality of execution services, observed execution costs should be adjusted for metaorder participation rate, size and duration to ensure that they are comparable across execution service providers. One of the exogenous factors which may bias measured execution costs are the different metaorder limit prices in the sample. Currently, there are no proposed methods to normalize for this bias. In the research, the difference in execution costs for metaorders with different limit prices was examined by implementing a limit order book simulation model. It was discovered that the difference in metaorder limit prices is a source of significant heterogeneity in the execution cost distribution. However, we were able to prove that when market agents trade with constant intensities, the difference in execution costs for metaorders with different limit prices is fully explained by their realized participation rate. As a result, financial institution may assess quality of execution services for metaorders without any reservations about differences in metaorders limit prices as long as execution costs are adjusted for different participation rates.

A competitive and profitable multi-agent autonomous broker for energy markets

Free and competitive energy markets are a recent and increasing phenomenon in several countries. Understanding these new energy markets and estimating their possible evolutions are current challenges of the research community. To avoid real market risks, the research community has developed autonomous traders and tested them in the Power Trading Agent Competition (Power TAC), a sophisticated energy market simulator. In this paper, we present COLDPower’16, a competitive autonomous trader composed of expert agents in specific kinds of markets and customers that combines local strategies into a global strategy to maximize profit. The local strategy of each tariff expert agent uses reinforcement learning algorithms, while the local strategy of the wholesale expert agent estimates future energy prices and the amount of energy that can be negotiated to buy energy when prices are low and sell energy when prices are high. COLDPower’16 was tested in Power TAC 2016. It achieved 2nd place in the final round of this international competition with 7 autonomous agent brokers.

Cryptocurrency, Delivery Lag, and Double Spending History

We develop a general equilibrium model of cryptocurrency to study a double spending prevention mechanism without payment confirmations. Agents trade cryptocurrency using a digital wallet, and the cryptocurrency system provides a means to verify a wallet's double spending history. Double spending can be prevented without payment confirmations under some conditions if a wallet has a good reputation for transaction history. As the difficulty of mining work increases, incentives for double spending decrease. We provide new insights into the properties of Bitcoin transaction fees, quantitatively assess the current Bitcoin system, and evaluate the welfare gain from fast transactions without payment confirmations.

Absolute vs. relative speed in high-frequency trading

This paper addresses the little investigated topic of the relationship between the speed of exchange servers, an absolute reference for the system, and trading speed, considered relative to the former. This is a major issue, as trading speed overwhelming the capability of the server to cope with the incoming orders might jeopardise the orderly functioning of the markets. It will be shown how, by raising the speed of trading and increasing the number of the agents operating in the market, it is possible to generate a crisis, no matter how performing the exchange server is. The paper presents a theoretical framework and then verifies its occurrence by analysing audit trail data. The theoretical framework shows a scenario in which under certain, heavy but by no means uncommon, conditions, the excess speed of the trading agents with respect to servers is capable of exacerbating price volatility, leading to vicious feedback loops capable of potentially creating a financial crisis. The empirical part analyses data taken from a particularly volatile day and compares them with much less volatile days. It results that, because of excessive speed, one of the most widely used techniques for minimising risk, order churning, can cause a major crisis.

Mean-Field Game Strategies for Optimal Execution

ABSTRACTAlgorithmic trading strategies for execution often focus on the individual agent who is liquidating/acquiring shares. When generalized to multiple agents, the resulting stochastic game is notoriously difficult to solve in closed-form. Here, we circumvent the difficulties by investigating a mean-field game framework containing (i) a major agent who is liquidating a large number of shares, (ii) a number of minor agents (high-frequency traders (HFTs)) who detect and trade against the liquidator, and (iii) noise traders who buy and sell for exogenous reasons. Our setup accounts for permanent price impact stemming from all trader types inducing an interaction between major and minor agents. Both optimizing agents trade against noise traders as well as one another. This stochastic dynamic game contains couplings in the price and trade dynamics, and we use a mean-field game approach to solve the problem. We obtain a set of decentralized feedback trading strategies for the major and minor agents, and express the solution explicitly in terms of a deterministic fixed point problem. For a finite population of HFTs, the set of major-minor agent mean-field game strategies is shown to have a -Nash equilibrium property where as .

COSMOS trader – Chaotic Neuro-oscillatory multiagent financial prediction and trading system

Over the years, financial engineering ranging from the study of financial signals to the modelling of financial prediction is one of the most stimulating topics for both academia and financial community. Not only because of its importance in terms of financial and commercial values, but more it vitally poses a real challenge to worldwide researchers and quants owing to its highly chaotic and almost unpredictable nature.This paper devises an innovative Chaotic Oscillatory Multi-agent-based Neuro-computing System (a.k.a. COSMOS) for worldwide financial prediction and intelligent trading. With the adoption of author's theoretical works on Lee-oscillator with profound transient-chaotic property, COSMOS effectively integrates chaotic neural oscillator technology into: 1) COSMOS Forecaster - Chaotic FFBP-based Time-series Supervised-learning agent for worldwide financial forecast and; 2) COSMOS Trader - Chaotic RBF-based Actor-Critic Reinforcement-learning agents for the optimization of trading strategies. COSMOS not only provides a fast reinforcement learning and forecast solution, more prominently it successfully resolves the massive data over-training and deadlock problems which usually imposed by traditional recurrent neural networks and RBF networks using classical sigmoid or gaussian-based activation functions.From the implementation perspective, COSMOS is integrated with 2048-trading day time-series financial data and 39 major financial signals as input signals for the real-time prediction and intelligent agent trading of 129 worldwide financial products which consists of: 9 major cryptocurrencies, 84 forex, 19 major commodities and 17 worldwide financial indices. In terms of system performance, past 500-day average daily forecast performance of COSMOS attained less 1% forecast percentage errors and with promising results of 8–13% monthly average returns.