Abstract: Reforms currently under way in China's electricity markets bear important implications for its decarbonization objectives. The southwestern province of Yunnan is among the provinces piloting the current iteration of power market reforms. As such, lessons from Yunnan will inform future market reform and renewable energy policies in China and potentially elsewhere. The dominance of hydropower in Yunnan's energy portfolio and the particular transmission constraints it faces, offer an interesting case study of the challenges of decarbonization. We report on market architecture reforms and aggregate market data collected from the Yunnan Power Exchange. We review four elements in the reformed market architecture. Market pricing rules, transitional quantity controls, the generation rights market, and inter-provincial trade. The specifics of market reform reflect a compromise between decarbonization, inter-provincial competition, grid security and development objectives and contribute to understanding of how the dual transitions of hydropower decarbonization and market liberalization interact. We conclude on six insights regarding the role of the grid operator, security checks on trade, integration of cascade hydropower, the inclusion of renewables in the generation rights market, price controls, and market participant price uncertainty.

Abstract: The increasing globalization of the Chinese economy has been enabled by both Chinese financial institutions operating globally as well as international firms operating within China. In geographical terms, this has been organized through a number of strategic cities serving as gateways for the exchange of financial functions, products and practices between China and the global economy. Drawing on location data of financial service firms in China listed on stock exchanges in Shenzhen, Shanghai and Hong Kong, this paper shows that Chinese financial firms are expanding globally and how Chinese financial centers are positioned and connected in the urban networks shaped by these financial service firms. It is found that Hong Kong, China, holds strategic positions in the integration of Chinese cities into global financial center networks, and that establishing a foothold in global financial centers such as New York and London has been a priority for Chinese financial institutions. The increasing capital flows directed by Chinese financial institutions suggests a shifting global financial geography, with numerous Chinese cities playing increasingly important roles within global financial center networks.

Abstract: High market uncertainty impedes an entrepreneur's ability to evaluate the state of the market for a business opportunity. For many entrepreneurial ventures, data collection and analysis techniques and technologies are becoming an important source to manage uncertainty. This trend is often referred to as “data-driven entrepreneurship.” We consider a dynamic approach using data to overcome market uncertainty for business opportunity-related evaluations. In particular, we examine the entrepreneur's investment portfolio in which each investment generates expected returns and some information about a specific aspect of the market for a single business opportunity. We develop a model that analyzes imperfect market data (e.g., financial, social, regulatory), while factoring in the entrepreneur's risk preference and operational shortages of resources, routines, reputation, and regulations. Our numerical findings show that, rather than pursuing the highest expected returns, an entrepreneur may choose perfect information, risk hedging, or market-controlling investments based on his/her cash level and risk preference. Hence, the entrepreneur, fueled by the availability of data analysis, could overcome uncertainties and obtain better insights for business opportunity decisions.

Abstract: Due to the development of financial markets, products, financial and mathematical models, portfolio selection today represents a comprehensive set of activities. Investors take into consideration many different factors, such as the market factors, return distribution characteristics and financial statements information. This research applies a Grey Relational Analysis (GRA) approach to evaluate the performance on a sample of stocks by taking those different factors into consideration. The results based upon a sample of 55 stocks for the trading year 2017 on the Croatian capital market show that using GRA approach in portfolio selection provides useful guidance for investors when making investment decisions, and better portfolio results in terms of risk and return are reachable compared to an equally weighted portfolio benchmark.

Abstract: The futures market plays a significant role in hedging and speculating by investors. Although various models and instruments are developed for real-time trading, it is difficult to realize profit by processing and trading a vast amount of real-time data. This study proposes a real-time index futures trading strategy that uses the KOSPI 200 index futures time series data. We construct a pattern matching trading system (PMTS) based on a dynamic time warping algorithm that recognizes patterns of market data movement in the morning and determines the afternoon’s clearing strategy. We adopt 13 and 27 representative patterns and conduct simulations with various ranges of parameters to find optimal ones. Our experimental results show that the PMTS provides stable and effective trading strategies with relatively low trading frequencies. Financial market investors are able to make more efficient investment strategies by using the PMTS. In this sense, the system developed in this paper contributes the efficiency of the financial markets and helps to achieve sustained economic growth.

Abstract: We develop a flexible methodology to protect marketing data in the context of a business ecosystem in which data providers seek to meet the information needs of data users, but wish to deter invalid use of the data by potential intruders. In this context we propose a Bayesian probability model that produces protected synthetic data. A key feature of our proposed method is that the data provider can balance the trade-off between information loss resulting from data protection and risk of disclosure to intruders. We apply our methodology to the problem facing a vendor of retail point-of-sale data whose customers use the data to estimate price elasticities and promotion effects. At the same time, the data provider wishes to protect the identities of sample stores from possible intrusion. We define metrics to measure the average and maximum loss of protection implied by a data protection method. We show that, by enabling the data provider to choose the degree of protection to infuse into the synthetic data, o...

Abstract: The versatility of the one†dimensional discrete wavelet analysis combined with wavelet and Burg extensions for forecasting financial times series with distinctive properties is illustrated with market data. Any time series of financial assets may be decomposed into simpler signals called approximations and details in the framework of the one†dimensional discrete wavelet analysis. The simplified signals are recomposed after extension. The final output is the forecasted time series which is compared to observed data. Results show the pertinence of adding spectrum analysis to the battery of tools used by econometricians and quantitative analysts for the forecast of economic or financial time series.

Abstract: In this study we aim to examine the effects of intellectual capital and itscomponents on companies’ market value and financial performance in Turkey. The financial and market data of production companies listed in Borsa Istanbul 100 index (BIST-100) for the periods 2011 through 2014 are used as dataset. We selected three different measures for financial performance; ROA, ROE and Net Profit Margin, and one measure for market value; Market to Book Ratio. As independent variables, we firstly took Modified Value Added Coefficient (M-VAIC), secondly we took three components of M-VAIC. Besides, we added natural logarithm of assets to control for variation in asset size of companies and tested its significance. The results suggest multi factor models are more powerful than single factor model in explaining the market performance and financial performance. The paper also reveals that models explaining financial performance provide more accurate results than the models of market performance. The analysis also exposes that physical capital and human capital has a significant effect on financial performance whereas physical capital and relational capital has an influence on market performance.

Abstract: Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market fluctuations can be impacted by various other information sources such as stock related events. Although some recent works propose event-driven prediction approaches by considering the event data, how to leverage the joint impacts of multiple data sources still remains an open research problem. In this work, we study how to explore multiple data sources to improve the performance of the stock prediction. We introduce an Extended Coupled Hidden Markov Model incorporating the news events with the historical trading data. To address the data sparsity issue of news events for each single stock, we further study the fluctuation correlations between the stocks and incorporate the correlations into the model to facilitate the prediction task. Evaluations on China A-share market data in 2016 show the superior performance of our model against previous methods.

Abstract: Electricity market price predictions enable energy market participants to shape their consumption or supply while meeting their economic and environmental objectives. By utilizing the basic properties of the supply-demand matching process performed by grid operators, known as Optimal Power Flow (OPF), we develop a methodology to recover energy market's structure and predict the resulting nodal prices by using only publicly available data, specifically grid-wide generation type mix, system load, and historical prices. Our methodology uses the latest advancements in statistical learning to cope with high dimensional and sparse real power grid topologies, as well as scarce, public market data, while exploiting structural characteristics of the underlying OPF mechanism. Rigorous validations using the Southwest Power Pool (SPP) market data reveal a strong correlation between the grid level mix and corresponding market prices, resulting in accurate day-ahead predictions of real time prices. The proposed approach demonstrates remarkable proximity to the state-of-the-art industry benchmark while assuming a fully decentralized, market-participant perspective. Finally, we recognize the limitations of the proposed and other evaluated methodologies in predicting large price spike values.

Abstract: Chapter Overview The technological revolution in the electric power system sector is producing large volumes of data with pertinent impact in the business and functional processes of system operators, generation companies, and grid users. Big data techniques can be applied to state estimation, forecasting, and control problems, as well as to support the participation of market agents in the electricity market. This chapter presents a revision of the application of data mining techniques to these problems. Trends like feature extraction/reduction and distributed learning are identified and discussed. The knowledge extracted from power system and market data has a significant impact in key performance indicators, like operational efficiency (e.g., operating expenses), investment deferral, and quality of supply. Furthermore, business models related to big data processing and mining are emerging and boosting new energy services.

Abstract: The size of the logistics market is typically estimated from the national accounting and market data. However, this data does not take certain in-house logistics services into account and most likely underestimates the true size of the market. The purpose of this paper is to develop a method for estimating the potential size of the logistics market in terms of overall logistics expenditure and to also account for in-house services.,The research approach involves combining longitudinal industry- and firm-level turnover data, incorporating survey data from Finland on logistics outsourcing and costs, and calculating yearly logistics expenditure and the market demand for logistics services. Descriptive statistics, weighted arithmetic means and analyses of variance are employed in the estimations.,The research suggests and demonstrates a rigorous method for estimating the size of the logistics market, including both market-based demand and in-house services.,The empirical data used to illustrate the result are limited to a single country. The methodology should be further validated with data from other countries. The quality of the survey data could be improved by targeting multiple informants from a single firm.,One outcome of the research is that policymakers will be better able to estimate the size of the logistics market on a national level. For service providers, the results provide additional information on the market potential of logistics services.,The novelty of the research lies in combining multiple data sources and expanding the estimation of the logistics market to include services provided in-house.

Abstract: Productivity improvement is considered the primary driver of economic growth in advanced countries because labour and capital are finite resources generating diminishing returns as their utilization increases. The financial services sector contributes to productivity growth in two ways: first, by improving its own output per worker and capital input (internal productivity) and, second, as a byproduct of the financial intermediation services it provides to the rest of economy (external productivity). Using OECD aggregate and sectoral productivity data, and performing a series of novel calculations, my analysis indicates that Canada’s financial sector over the last 15 years has lagged behind other OECD countries in its contribution to productivity growth. As well, Canada has experienced low aggregate productivity levels and growth rates over the same time period. Improving the financial sector’s productivity would boost not only the sector’s performance but also the economy as a whole. This Commentary shows that part of the explanation for these relatively poor results include a policy approach that does not properly evaluate the link between competition and productivity, a regulatory structure that does not always reflect international best practices, and less efficient allocation of capital. As a result, this Commentary recommends the following: • Remove barriers to the development of fintechs through a functional approach to regulation; • Implement regulatory oversight that is proportionate to functional risk; • Consider whether a more explicit productivity mandate is useful for Canadian regulators, in part based on the innovative ideas coming out of the UK’s Financial Conduct Authority’s focus on competition and productivity; • Revise the Bank Act and Insurance Companies Act to allow more flexibility for banks and insurance companies to make substantial investments in fintechs and insuretechs; • Since it is unlikely politically to have one (or twin) national financial-sector regulator(s) with legislative/ statutory powers, focus on achievable goals such as making clear what arrangements are in place between federal and provincial regulators for the sharing of market data related to, for example, the analysis of financial stability in capital markets, and strengthen links between market-conduct regulators across provinces and functions; and • Reduce incentives for banks to lend to less productive residential mortgages by charging lenders mortgage-insurance premiums that reflect idiosyncratic risk beyond just loan-to-value ratios.

Abstract: Stock market prediction is one of the most attractive research topic since the successful prediction on the market's future movement leads to significant profit. Traditional short term stock market predictions are usually based on the analysis of historical market data, such as stock prices, moving averages or daily returns. However, financial news also contains useful information on public companies and the market. Existing methods in finance literature exploit sentiment signal features, which are limited by not considering factors such as events and the news context. We address this issue by leveraging deep neural models to extract rich semantic features from news text. In particular, a Bidirectional-LSTM are used to encode the news text and capture the context information, self attention mechanism are applied to distribute attention on most relative words, news and days. In terms of predicting directional changes in both Standard & Poor's 500 index and individual companies stock price, we show that this technique is competitive with other state of the art approaches, demonstrating the effectiveness of recent NLP technology advances for computational finance.

Abstract: Drawing on recent contributions inferring financial interconnectedness from market data, our paper provides new insights on the evolution of the US financial industry over a long period of time by using several tools coming from network science. Relying on a Time-Varying Parameter Vector AutoRegressive (TVP-VAR) approach on stock market returns to retrieve unobserved directed links among financial institutions, we reconstruct a fully dynamic network in the sense that connections are let to evolve through time. The financial system analysed consists of a large set of 155 financial institutions that are all the banks, broker-dealers, insurance and real estate companies listed in the Standard & Poors' 500 index over the 1993-2014 period. Looking alternatively at the individual, then sector-, community- and system-wide levels, we show that network sciences' tools are able to support well-known features of the financial markets such as the dramatic fall of connectivity following Lehman Brothers' collapse. More importantly, by means of less traditional metrics, such as sectoral interface or measurements based on contagion processes, our results document the co-existence of both fragmentation and integration phases between firms independently from the sectors they belong to, and doing so, question the relevance of existing macroprudential surveillance frameworks which have been mostly developed on a sectoral basis. Overall, our results improve our understanding of the US financial landscape and may have important implications for risk monitoring as well as macroprudential policy design.

Abstract: Smallholder farmers in developing countries face tough challenges to their productivity, growth, and sustainability—including lack of access to affordable financial products, limited knowledge of high-quality inputs, low usage of technology and market data, and poor market links across the value chain. To close these gaps and help smallholder farmers thrive, social enterprises are implementing innovative solutions in the agriculture sector to serve them. Social enterprises are defined as private for-profit, nonprofit, or hybrid organizations that use business methods to advance their social mission. In the case of agriculture, social enterprises often address a particular pain point in the value chain, with the intention that the cost of their services or products will be recuperated by the benefits and income gains that smallholders will achieve. To serve such a “last mile” market, social enterprises will often develop a business model that is innovative, cost-effective, and provides strong value for money in providing quality services and products.The purpose of this book is to showcase the market-based solutions that have proven effective at supporting smallholders and to synthesize the experiences of social enterprises around the world. This book catalogues more than 100 social enterprises, categorized into 9 business models, that cut across the agriculture value chain.

Abstract: We present a simple model of a non-equilibrium self-organizing market where asset prices are partially driven by investment decisions of a bounded-rational agent. The agent acts in a stochastic market environment driven by various exogenous "alpha" signals, agent's own actions (via market impact), and noise. Unlike traditional agent-based models, our agent aggregates all traders in the market, rather than being a representative agent. Therefore, it can be identified with a bounded-rational component of the market itself, providing a particular implementation of an Invisible Hand market mechanism. In such setting, market dynamics are modeled as a fictitious self-play of such bounded-rational market-agent in its adversarial stochastic environment. As rewards obtained by such self-playing market agent are not observed from market data, we formulate and solve a simple model of such market dynamics based on a neuroscience-inspired Bounded Rational Information Theoretic Inverse Reinforcement Learning (BRIT-IRL). This results in effective asset price dynamics with a non-linear mean reversion - which in our model is generated dynamically, rather than being postulated. We argue that our model can be used in a similar way to the Black-Litterman model. In particular, it represents, in a simple modeling framework, market views of common predictive signals, market impacts and implied optimal dynamic portfolio allocations, and can be used to assess values of private signals. Moreover, it allows one to quantify a "market-implied" optimal investment strategy, along with a measure of market rationality. Our approach is numerically light, and can be implemented using standard off-the-shelf software such as TensorFlow.

Abstract: Financial institutions and markets occupy a key place in the economic and social well-being of individuals, companies and societies but, if they are not managed adequately, this can have important consequences, also in ethical terms. This work is a simple and brief explanation of the ethical problems posed by institutions, markets and financial products.

Abstract: This thesis demonstrates the use of deep learning for automating hourly price forecasts in continuous intraday electricity markets, using various types of neural networks on comprehensive sequential market data and cutting-edge image processing networks on spatio-temporal weather forecast maps. Deep learning is a subfield of artificial intelligence that excels on problems such as these with multifarious input data and manifold interacting factors. It has seen tremendous success on a range of problems across industries, and while it is important to have realistic expectations, there is little reason to believe that intraday electricity markets are different. Focusing on Nord Pool’s intraday market Elbas, we predict Nordic buyers’ volume-weighted average price over the last six hours of trading prior to each delivery hour. Aggregating this window gives buyers flexibility from many trades and sufficient time in which to act on the predictions, and solves issues with data sparsity while keeping sufficient resolution for predictions to be informative. We develop various neural networks via extensive experimentation, with inspiration from other research and problem domains. To make the findings relevant in practice, we impose constraints on the input data based on what would be available to Elbas market participants six trading hours ahead of delivery. The neural networks are benchmarked against a set of simple domainbased heuristics and traditional methods from econometrics and machine learning. We conclude with a holistic evaluation of the efficacy of deep learning on our problem, whether it is economically justifiable in light of its value-add, what the salient hurdles are to implementing it in practice, and what the implications are for broader applications of AI in intraday markets. The deep learning models1 are relatively accurate and reliable under normal market conditions. The average price across all delivery hours in the held-out data is 30.95 EUR/MWh, where our best network is on average off by 2.72 EUR/MWh. It beats the best simple heuristic by 21–25%, and the best benchmark model by 12–16%. The network also anticipates major fluctuations in prices relatively consistently, and generally outperforms all alternative methods when prices are especially volatile or trading activity particularly high. In contrast to the benchmarks, there are also ample avenues for improving the network further. Beyond being promising in its own right, we also argue that the network demonstrates the wider potential of deep learning in a range of applications in intraday markets, and that these are worthy of serious consideration — though one should be aware of the practical hurdles to implementing them operationally. The Python-code for training and evaluating our final neural networks is available on our public Github repository at: https://github.com/johannes-kk/Elbas-Deep-Learning.

Abstract: Latent order book models have allowed for significant progress in our understanding of price formation in financial markets In particular they are able to reproduce a number of stylized facts, such as the square-root impact law An important question that is raised -- if one is to bring such models closer to real market data -- is that of the connection between the latent (unobservable) order book and the real (observable) order book Here we suggest a simple, consistent mechanism for the revelation of latent liquidity that allows for quantitative estimation of the latent order book from real market data We successfully confront our results to real order book data for over a hundred assets and discuss market stability One of our key theoretical results is the existence of a market instability threshold, where the conversion of latent order becomes too slow, inducing liquidity crises Finally we compute the price impact of a metaorder in different parameter regimes

Abstract: Since the financial crisis, investors have enjoyed generally benign conditions, with subdued volatility and strong markets - but active equity managers have remained under pressure. Yet this should not be surprising; history has shown a strong pattern of counter-cyclicality in manager excess returns relative to the equity market. In this study, the authors take a close look at the relationship between equity market conditions (defined by market returns, volatility, and dispersion) and active equity manager results. Focusing on the US large cap space, they analyze over 20 years of manager and market data to determine which set of conditions are associated with more or less favorable results for active equity managers.

Abstract: License Authors of papers retain copyright and release the work under a Creative Commons Attribution 4.0 International License (CC-BY). The University of Durham runs the Nomis database of labour market statistics on behalf of the UK’s Office for National Statistics (1981). As of publication, Nomis contains 1,249 datasets, almost all of which are based around differing statistical geographies. All the data is freely available and does not require users to create accounts to download data, and Nomis provides an interactive web platform for downloading data. However, like all GUI downloading systems, there is a risk that users will select the wrong option without realising their mistake, and downloading multiple datasets is tedious, repetitive work. The nomisr package provides functions to identify datasets available through Nomis, the variables and query options for those datasets, and a function for downloading data, including combining large datasets into a single tibble (Müller and Wickham 2018)

Abstract: We present a simple model of a non-equilibrium self-organizing market where asset prices are partially driven by investment decisions of a bounded-rational agent. The agent acts in a stochastic market environment driven by various exogenous "alpha" signals, agent's own actions (via market impact), and noise. Unlike traditional agent-based models, our agent aggregates all traders in the market, rather than being a representative agent. Therefore, it can be identified with a bounded-rational component of the market itself, providing a particular implementation of an Invisible Hand market mechanism. In such setting, market dynamics are modeled as a fictitious self-play of such bounded-rational market-agent in its adversarial stochastic environment. As rewards obtained by such self-playing market agent are not observed from market data, we formulate and solve a simple model of such market dynamics based on a neuroscience-inspired Bounded Rational Information Theoretic Inverse Reinforcement Learning (BRIT-IRL). This results in effective asset price dynamics with a non-linear mean reversion - which in our model is generated dynamically, rather than being postulated. We argue that our model can be used in a similar way to the Black-Litterman model. In particular, it represents, in a simple modeling framework, market views of common predictive signals, market impacts and implied optimal dynamic portfolio allocations, and can be used to assess values of private signals. Moreover, it allows one to quantify a "market-implied" optimal investment strategy, along with a measure of market rationality. Our approach is numerically light, and can be implemented using standard off-the-shelf software such as TensorFlow.

Abstract: This research seeks to design, implement, and test a fully automatic high-frequency trading system that operates on the Chilean stock market, so that it is able to generate positive net returns over time. A system that implements high-frequency trading (HFT) is presented through advanced computer tools as an NP-Complete type problem in which it is necessary to optimize the profitability of stock purchase and sale operations. The research performs individual tests of the algorithms implemented, reviewing the theoretical net return (profitability) that can be applied on the last day, month, and semester of real market data. Finally, the research determines which of the variants of the implemented system performs best, using the net returns as a basis for comparison. The use of particle swarm optimization as an optimization algorithm is shown to be an effective solution since it is able to optimize a set of disparate variables but is bounded to a specific domain, resulting in substantial improvement in the final solution.

Abstract: The Brazilian electricity market is characterized by having around 65% of its installed capacity coming from hydropower plants, with multiple agents coexisting in the same hydro cascades. Currently, it also contains certain peculiarities that distinguish it from other markets, such as the Energy Reallocation Mechanism (MRE), a centerpiece of the Brazilian market’s design. This paper proposes replacing the MRE with a bid-based short-term market called the virtual reservoir model. To simulate the behavior of the hydros in this new market, an agent-based model is implemented using the reinforcement Q-learning algorithm, simulated annealing and linear programming. In the simulations, we use real data – encompassing more than 98% of the total hydro installed capacity and three years of market data – from the Brazilian power system. The results indicate that the management of (virtual) reservoirs can be the responsibility of each hydro: these can save water according to their own risk perceptions, while maintaining current efficiency and security levels. The results also suggest that the final monthly short-term market prices can substantially decrease in comparison with the current prices.

Abstract: Stock market prediction is one of the most attractive research topic since the successful prediction on the market's future movement leads to significant profit. Traditional short term stock market predictions are usually based on the analysis of historical market data, such as stock prices, moving averages or daily returns. However, financial news also contains useful information on public companies and the market. Existing methods in finance literature exploit sentiment signal features, which are limited by not considering factors such as events and the news context. We address this issue by leveraging deep neural models to extract rich semantic features from news text. In particular, a Bidirectional-LSTM are used to encode the news text and capture the context information, self attention mechanism are applied to distribute attention on most relative words, news and days. In terms of predicting directional changes in both Standard & Poor's 500 index and individual companies stock price, we show that this technique is competitive with other state of the art approaches, demonstrating the effectiveness of recent NLP technology advances for computational finance.

Abstract: The dynamics of financial markets are discussed. After a brief introduction of the price formation process, we review the statistical features (also known as “stylized facts”) of stock return time series, which exhibit fat tails and intermittent periods of higher or lower volatility. Several models aimed at understanding the mechanisms that lead to these seemingly ubiquitous features of financial markets are then reviewed. Those models have largely been developed within the Econophysics community but we emphasize here that they all contain elements consistent with a Synergetic approach.