Energy market rules should incentivize market participants to behave in a market and grid conform way. However, they can also provide incentives for undesired and unexpected strategies if the market design is flawed. Multi-agent Reinforcement learning (MARL) is a promising new approach to predicting the expected profit-maximizing behavior of energy market participants in simulation. However, reinforcement learning requires many interactions with the system to converge, and the power system environment often consists of extensive computations, e.g., optimal power flow (OPF) calculation for market clearing. To tackle this complexity, we provide a model of the energy market to a basic MARL algorithm in the form of a learned OPF approximation and explicit market rules. The learned OPF surrogate model makes an explicit solving of the OPF completely unnecessary. Our experiments demonstrate that the model additionally reduces training time by about one order of magnitude but at the cost of a slightly worse performance. Potential applications of our method are market design, more realistic modeling of market participants, and analysis of manipulative behavior.

For this reason, their applicability in practice is limited. Growing environmental concerns and advancements in communication The above-mentioned scalability issues can be addressed and monitoring technologies have led to the increased by employing deep RL methods like the Deep Deterministic deployment of Distributed Energy Resources (DERs) Policy Gradient (DDPG) algorithm [10], which utilizes neural in power networks [1], comprising renewable energy sources networks to extend the Q-learning capabilities to continuous and prosumers. The market integration of these units is facilitated state and action spaces. The authors in [11]-[13] propose deep by their large-scale aggregation under financial entities, RL methods for the economic dispatch and market participation commonly known as Virtual Power Plants (VPPs), which have of DERs aggregated in a VPP. The main limitation the capacity for trading in wholesale electricity markets [2], of these works is that they fail to account for the complex [3]. As a self-interested market participant, a VPP aims at internal physical constraints of large-scale VPPs, such as maximizing its own profit generated by its market participation power generation limits and power flow constraints, in order to and the fulfillment of contractual obligations towards its ensure a safe operation.

Agent-based models (ABMs) are fit to model heterogeneous, interacting systems like financial markets. We present the latest advances in Evology: a heterogeneous, empirically calibrated market ecology agent-based model of the US stock market. Prices emerge endogenously from the interactions of market participants with diverse investment behaviours and their reactions to fundamentals. This approach allows testing trading strategies while accounting for the interactions of this strategy with other market participants and conditions. Those early results encourage a closer association between ABMs and ML algorithms for testing and optimising investment strategies using machine learning algorithms.

Welcome to insideBIGDATA's "Heard on the Street" round-up column! In this regular feature, we highlight thought-leadership commentaries from members of the big data ecosystem. Each edition covers the trends of the day with compelling perspectives that can provide important insights to give you a competitive advantage in the marketplace. We invite submissions with a focus on our favored technology topics areas: big data, data science, machine learning, AI and deep learning. Data is the new oil.

We present a new financial framework where two families of RL-based agents representing the Liquidity Providers and Liquidity Takers learn simultaneously to satisfy their objective. Thanks to a parametrized reward formulation and the use of Deep RL, each group learns a shared policy able to generalize and interpolate over a wide range of behaviors. This is a step towards a fully RL-based market simulator replicating complex market conditions particularly suited to study the dynamics of the financial market under various scenarios.

Having studied and worked in the realm of finance, I had the opportunity to witness and also experience what it is like to immerse in the crazy world that is the financial markets. With the increasing prevalence of Artificial Intelligence, hedge fund managers, asset managers, portfolio managers and almost every other market participant trying to'beat' the market are trying to find new, innovative ways to generate alpha. To the layman, it simply means "how do I make money by buying and selling financial instruments"? Why then is the financial markets such an attractive place for people trying to make it big? The answer is simple -- a lot of money can be made in a very short period of time with a low capital requirement, if you know what you are doing (strong caveat here).

As part of a successful strategy, the value of a company should be increased in a targeted manner through the creation of a sustainable competitive advantage. The business model plays an essential role in this regard. The strategic alignment of the business model with customer requirements and satisfaction requires the model to chart the associated value chain in its macroeconomic environment. However, the sustainability and profitability of a business model is always limited in time, since progress and innovation not only promote competition, but also have the power to make whole business models obsolete. The theme of digitalisation has long exerted a clear influence through various trends and technologies in the private (social media, smart home, mobile internet, etc.) and business environments (3D printing, advanced robotics, machine learning, etc.)

Over the past few years, the Canada Revenue Agency has been using data analytics and AI, such as machine-learning algorithms that predict tax non-compliance and detect activity in the underground economy. Since 2018, the Department of Justice Canada has licensed the use of Tax Foresight, AI software developed by Blue J Legal Inc. in Toronto, which employs machine learning to predict – with about 90% accuracy, according to the company – how a court might rule on a particular tax scenario. "It's not just about speeding up [analysis] that would otherwise happen," says Benjamin Alarie, co-founder and CEO of Blue J Legal and Osler Chair of Business Law at the University of Toronto. "It's about making [widely] available a really good prediction that would otherwise be the domain of an experienced [lawyer]." AI technology could bring more certainty to the interpretation of tax law, Alarie adds: "Everyone benefits from that."

Throughout the past year, the use of artificial intelligence (AI) and other forms of technology within the financial services industry has continued apace. This will increase further as it dovetails with enriched natural language processing (NLP) through 2020 and into the coming decade and lead to more personalisation of services. Indeed, as noted in Crowdfund Insider, the European Union is to invest €100 million in artificial intelligence and blockchain start-ups next year, to boost the EU-wide innovation ecosystem. Globally, the Fintech revolution offers solutions to all manner of issues, and as we see in so many sectors, algorithms and AI can locate data and highlight trends. In doing so, such technologies operate automatically – and therefore can carry out functions much quicker than by human effort – and at a reduced financial cost as technology mitigates the need for large data-crunching teams.

One of the most critical capabilities to responding to change and disruption in the marketplace is the ability to sense the change in a manner and, most importantly, timeframe that allows a response to be identified and executed. The frequency and discontinuous nature of change rocking the market requires a robust process that takes into account as many factors as possible to identify the change. This process then must describe factors and relationships to allow them to be analyzed to develop the response. The difficulty lies in the volume of data, both new and old, that must be taken into account to first identify the change and second to guide in determining a response. This is where data analytics practices utilizing artificial intelligence comes into the equation to support the business.