Natural language processing is a critical part of the digital transformation. NLP enables user-friendly interactions between machine and human by making computers understand human languages. Intelligent chatbot is an essential application of NLP to allow understanding of users’ utterance and responding in understandable sentences for specific applications simulating human-to-human conversations and interactions for problem solving or Q&As. This research studies emerging technologies for NLP-enabled intelligent chatbot development using a systematic patent analytic approach. Some intelligent text-mining techniques are applied, including document (...) term frequency analysis for key terminology extractions, clustering method for identifying the subdomains, and Latent Dirichlet Allocation for finding the key topics of patent set. This research utilizes the Derwent Innovation database as the main source for global intelligent chatbot patent retrievals. (shrink)

A Critical Notice of Liba Taub, Ancient Meteorology, Routledge, London and New York, 2003.

_Purpose._ The paper attempts to investigate the constructivist approach to the social world and its implications for social forecasting. _Theoretical basis._ Social forecasting is mainly based on the idea that a human is "determined ontologically". Using the methodology of the natural sciences, most predictions and forecasts fail to encompass all the multiplicity and variability of the future. The postmodern interpretation of reality gave impetus to the development of the new approaches to it. A constructivist approach to social reality began to (...) compete with essentialism. Social constructivism asserts that reality is a set of mental constructs, that it is ultimately a text. Radical constructivism interprets reality as a specific system of meanings emphasizing the artifact aspects of our reality. An interpretation of the social actors’ behavior is based on the ways of understanding accepted in a given society/community and do not possess ontological universality. The creators of social space are also its creations. _Originality._ Within the framework of the postmodern approach to reality, the second-order forecasting, or forecasting of forecasting, is particularly relevant. That means that the observers-forecasters must be included in the forecast as a part of one-unified process. At this stage, a forecaster must realize that he/she is a part of a larger system, a part of the world he/she observes (and actually creates). The situation changes dramatically – the forecaster is forced to take responsibility for his/her own observations. This ultimately leads to the "humanization" of forecasting. Acting in our world full of uncertainty, unpredictability, and turbulence, modern researchers of the future should be mindful of powerful social constructs of reality. _Conclusions._ Social forecasting should be embedded in a wider context, which requires a joint effort of philosophers, foresight practitioners, historians, psychologists, sociologists, political scientists, religious scholars, anthropologists, etc. To develop promising visions and scenarios of the future, it is necessary to answer the question "Why?", which is the task of philosophically oriented research, because without this answer, we will deal with the consequences; and the implementation of the negative scenarios will reproduce itself in new socio-cultural and historical conditions. An in-depth understanding of this "Why?" provides opportunities to be in the flow of transformations. The study of the deep mental processes of the actors of social changes, the multidimensional influence on the transformation of social structures can gradually expand an answer to the question "Why?", that can cause positive changes and, accordingly, allow to create fruitful projects of the future and form effective behavioral strategies that correspond to the desired level of social development. (shrink)

Forecasting involves an underlying conceptualization of probability. It is this that gives sense to the notion of precision in number that makes us think of economic forecasting as more than simply complicated guesswork. We think of it as well-founded statement, a science and not an art of numbers. However, this understanding is at odds with the nature of social reality and the attributes of the forecaster. We should think differently about how we both anticipate and make the future and (...) what this means. Foresight is perhaps a more appropriate term. This paper addresses two issues that rarely receive attention in the field of economics. First, why is there a continued high demand for economic forecasts despite their lack of success in anticipating significant turning points in any given system? Second, what are forecasts actually assuming about the nature of a system and the future state of the world? In the paper I approach these issues indirectly. My intention is to highlight their significance by setting out a series of arguments that encapsulate the characteristics of a forecaster required to match a common understanding of what forecasting is intended to do. The structure of this paper is unusual for a contribution in the field of economics. It follows a format more commonly used in analytical philosophy when the author wants to focus on a problem and where the intention is to provoke further questioning, rather than supply ready answers. As such, it should not be read as a comprehensive account of all possible approaches to methods or philosophies of forecasting and attendant issues of probability. Three points are worth stating at the outset as a guide to what follows: Forecasting tends to forget that it is conjecture and what that really means. Its scientism overburdens how it is articulated and how it is perceived. We tend to think of forecasting as degrees of precision in prediction and of successful prediction as successful description of phenomena at some future point. There is, as the following discussion demonstrates, something basically inconsistent within the implications of this minimalism. Since the greater part of the credibility of, and authority of, economics resides in its claims to effective forecasting these points are highly relevant to the state of the discipline. Read the Open Peer Discussion on this paper ». (shrink)

In the traditional decision theories the role of forecasts is to a large extent swept under the carpet. I believe that a recognition of the connections between forecasts and decisions will be of benefit both for decision theory and for the art of forecasting.In this paper I have tried to analyse which factors, apart from the utilities of the outcomes of the decision alternatives, determine the value of a decision. I have outlined two answers to the question why a (...) decision which is made on the basis of a forecast is better than a decision which is based on a guess. Neither of these answers is universally valid. An assumption which is necessary for the first answer, i.e. Good's result, is that Bayes' rule is accepted as a correct and generally applicable decision principle. The second answer, which was given with the aid of probability intervals, departed from a more general decision principle, the maximin criterion for expected utilities, which was formulated in order to evade some of the criticism against Bayes' rule. However, the argument leading to the ansser is based on the assumption that the probability intervals associated with the states of nature represent certain knowledge. For this reason this answer is only approximatively valid.As a number of quotations in the section on “the weight of evidence” show, it is not sufficient to describe the knowledge about the states of nature by a single number, representing the (subjective) probability of the state, but something else has to be invoked which measures the amount of information on which a decision is based. Several authors have tried to characterize this mysterious quantity, which here was called the weight of evidence. However, there seems to be little agreement as to how this quantity should be measured. (shrink)

Purpose of the article is to predict the interrelationship between the change of financial institutions loan portfolio and activities of the main economic sectors in Lithuania. Coherence between financial intermediation and economic growth cause a great interest of economists during the late decade. Prevailed opinion that banking sector is the reflection of economic growth and expansion and that its role - to intermediate in the saving and investing needs, reallocating funds between economic activities, was replaced by sentiment that strong and (...) stable banking sector could be not only the result of economic development, but also the cause of this growth. The purpose of the article is to accomplish forecast of the influence of financial institutions loan portfolio change to the main economic sectors in Lithuania for 2013-2017 period. Methodology/methods Analysis of variation of loan portfolio according economic sectors shows the tendencies of financing of various activities in the past. Regression - correlation analysis helps to identify the influence of loan portfolio changes and their impact for GDP and employment in separate economic sectors. The forecasting of different economic sectors was made using extrapolation methods and econometric method. Scientific aim: Economic situation in Lithuania forces to estimate decisions made by banking sector that influence not only individual countries but also the global economy. In this regard, there is a natural question of whether the process of underway stagnation should be judged as a timely economic development stage, or perhaps as the result of policies pursued by financial institutions? Prerequisites for the problem situation forces to overhaul loan portfolio managed by financial institutions, evaluate its change on the country's economy sectors, and to investigate these relationships forecasts. Findings: There is a strong link between financial sector development and economic growth. The results showed that the volume of loans has a very close interdependence with the GDP. Data obtained for loan portfolio forecasting for 2013-2017 showed that the growth of loans can be seen in all sectors except construction. Employment should grow only in public and retail sectors. Conclusions : The most relationship with GDP was established in retail and public sectors. Determining the correlation coefficients and regression equations between loans and employment the strongest relationship found in retail, industrial and construction sectors. The study encountered lack of data for 2012, since the information about the composition of the loan portfolio in different sectors since November 2011 is no longer provided to the Bank of Lithuania. (shrink)

Predicting the future state of a system has always been a natural motivation for science and practical applications. Such a topic, beyond its obvious technical and societal relevance, is also interesting from a conceptual point of view. This owes to the fact that forecasting lends itself to two equally radical, yet opposite methodologies. A reductionist one, based on first principles, and the naïve-inductivist one, based only on data. This latter view has recently gained some attention in response to the availability (...) of unprecedented amounts of data and increasingly sophisticated algorithmic analytic techniques. The purpose of this note is to assess critically the role of big data in reshaping the key aspects of forecasting and in particular the claim that bigger data leads to better predictions. Drawing on the representative example of weather forecasts we argue that this is not generally the case. We conclude by suggesting that a clever and context-dependent compromise between modelling and quantitative analysis stands out as the best forecasting strategy, as anticipated nearly a century ago by Richardson and von Neumann. (shrink)

The article discusses the problem of the possibility of knowing the future, especially the future of social phenomena compared with the future of natural ones. This problem is formulated as a dilemma: the future can be explored or can be only constructed. The idea of constructive character of knowledge of the future is viewed in two possible interpretations.The first one is a special case of the constructivist interpretation of knowledge, according to which different pictures of the future are arbitrarily constructed (...) on the basis of information about the past and current state. The second interpretaion can be presented in the form of a praxeological question: what should be an action in relation to the future, first and foremost to the future of social phenomena - cognitive or creative. It is shown that, in the first case, there is an ability to interpret knowledge of the future from the point of view of epistemological realism, in the second case, both cognitive and creative types of activity as a pragmatic position in relation to the future are necessary and cognitive activity cannot be reduced to creative one. It is also shown that forecaster’s dilemma reflects the problematic nature of forecasting under the conditions of transformation of scientific rationality and point of view of common sense, which is observed in recent decades. (shrink)

The TV show rating analysis and prediction system can collect and transmit information more quickly and quickly upload the information to the database. The convolutional neural network is a multilayer neural network structure that simulates the operating mechanism of biological vision systems. It is a neural network composed of multiple convolutional layers and downsampling layers sequentially connected. It can obtain useful feature descriptions from original data and is an effective method to extract features from data. At present, convolutional neural networks (...) have become a research hotspot in speech recognition, image recognition and classification, natural language processing, and other fields and have been widely and successfully applied in these fields. Therefore, this paper introduces the convolutional neural network structure to predict the TV program rating data. First, it briefly introduces artificial neural networks and deep learning methods and focuses on the algorithm principles of convolutional neural networks and support vector machines. Then, we improve the convolutional neural network to fit the TV program rating data and finally apply the two prediction models to the TV program rating data prediction. We improve the convolutional neural network TV program rating prediction model and combine the advantages of the convolutional neural network to extract effective features and good classification and prediction capabilities to improve the prediction accuracy. Through simulation comparison, we verify the feasibility and effectiveness of the TV program rating prediction model given in this article. (shrink)

Public policy and public opinion directly affect the image of the government, but due to the lack of appropriate monitoring and early warning tools, the government’s handling of credit changes is seriously lagging behind. In response to this problem, this paper integrates the internet, public information, market credit information, and other data, uses hidden Markov models and natural language processing technology, and establishes a modern government public policy and public opinion monitoring and early warning model to evaluate government credit in (...) real time; the government can formulate relevant policies based on the evaluation results to improve the government’s governance capabilities. Empirical analysis shows that, based on the dynamic scoring framework and Markov model, the government credit monitoring and early warning models established, respectively, have 90% of the reference value, and the analysis results have the same reference. This method can effectively predict the trend of hot online public opinion. The subsequent establishment of an online public opinion early warning system and an online public opinion guidance mechanism provided theoretical support. (shrink)

A startup ecosystem is a dynamic environment in which several actors, such as investors, venture capitalists, angels, and facilitators, are the protagonists of a complex interplay. Most of these interactions involve the flow of capital whose size and direction help to map the intricate system of relationships. This quantity is also considered a good proxy of economic success. Given the complexity of such systems, it would be more desirable to supplement this information with other informative features, and a natural choice (...) is to adopt mathematical measures. In this work, we will specifically consider network centrality measures, borrowed by network theory. In particular, using the largest publicly available dataset for startups, the Crunchbase dataset, we show how centrality measures highlight the importance of particular players, such as angels and accelerators, whose role could be underestimated by focusing on collected funds only. We also provide a quantitative criterion to establish which firms should be considered strategic and rank them. Finally, as funding is a widespread measure for success in economic settings, we investigate to which extent this measure is in agreement with network metrics; the model accurately forecasts which firms will receive the highest funding in future years. (shrink)

In the midst of the ultra modernity of stock exchanges and financial markets, certain practitioners are increasingly using forecasting models of changes in rates whose scientific rationality is particularly contested. We refer to ‘technical analysis’, or, in the jargon of finance, of ‘chartism’. The adherents of this practice affirm that their models offer the possibility of detecting and of reading, by means of stereotyped graphical configurations, rising or falling market trends. Now, for a large number of people who hold scientific (...) economic and financial theories to describe the ‘nature’ of changes in rates as so many random and unpredictable phenomena, these models arise above all from the sphere of ‘superstition’ and ‘beliefs’, in the worst sense of the term. To listen to them, one would think there was hardly any difference between sorcery, prophecy, and chartism, since in short: “it works because people believe in it”. These are remarks that can only arouse the curiosity of the anthropologist, because they actually serve merely to recall epistemologica! controversies that depend on the rationality and the irrationality of observed practices and debates in various cultures. At the heart of these contradictory debates, it is precisely prophecy as a cultural mode of managing unforeseen events that has been the subject of multiple anthropological, historical, and epistemological studies which can, in a comparative perspective, clarify the structure and functioning of forecasting tools employed by the chartists in the context of financial speculation. (shrink)

The novel coronavirus disease is regarded as one of the most imminent disease outbreaks which threaten public health on various levels worldwide. Because of the unpredictable outbreak nature and the virus’s pandemic intensity, people are experiencing depression, anxiety, and other strain reactions. The response to prevent and control the new coronavirus pneumonia has reached a crucial point. Therefore, it is essential—for safety and prevention purposes—to promptly predict and forecast the virus outbreak in the course of this troublesome time to (...) have control over its mortality. Recently, deep learning models are playing essential roles in handling time-series data in different applications. This paper presents a comparative study of two deep learning methods to forecast the confirmed cases and death cases of COVID-19. Long short-term memory and gated recurrent unit have been applied on time-series data in three countries: Egypt, Saudi Arabia, and Kuwait, from 1/5/2020 to 6/12/2020. The results show that LSTM has achieved the best performance in confirmed cases in the three countries, and GRU has achieved the best performance in death cases in Egypt and Kuwait. (shrink)

Cosmology seems extremely remote from everyday human practice and experience. It is usually taken for granted that cosmological data cannot rationally influence our beliefs about the fate of humanity—and possible other intelligent species—except perhaps in the extremely distant future, when the issue of “heat death” (in an ever-expanding universe) becomes actual. Here, an attempt is made to show that it may become a practical question much sooner, if an intelligent community wishes to maximize its creative potential. We estimate, on the (...) basis of a greatly simplified model, the rate of loss of potentially useful information due to the delay in undertaking the colonization of the largest gravitationally bound structures in an accelerating universe. In addition, we argue for a natural cosmological extension of the classical taxonomy of advanced technological communities given by Kardashev. New developments in the fields of anthropic self-selection and physical eschatology give, for the first time, solid foundations to such results. This may open some new (and possibly urgent) issues in the areas of future policy making and transhumanist studies generally. It may also give us a slightly better perspective on the SETI endeavor. (shrink)

Introduction:Can nature be controlled?. Autonomous nature -- Greco-Roman concepts of nature -- Christianity and nature -- Nature personified : Renaissance ideas of nature -- Controlling nature. Vexing nature : Francis Bacon and the origins of experimentation -- Natural law : Spinoza on natura naturans and natura naturata -- Laws of nature :Lleibniz and Newton -- Epilogue : rambunctious nature in the twenty-first century.

Standalone corporate social responsibility reports vary considerably in the content of information released due to their voluntary nature. In this study, we develop a disclosure score based on the tone, readability, length, and the numerical and horizon content of CSR report narratives, and examine the relationship between the CSR disclosure scores and analyst forecasts. We find that CSR reporters with high disclosure scores are associated with more accurate forecasts, whereas low score CSR reporters are not associated with more accurate (...) forecasts than firms who do not issue CSR reports. The findings are robust to controlling for firm characteristics including CSR activity ratings and financial narratives. The findings are driven by experienced CSR reporters rather than first-time CSR reporters. Together, our findings suggest that the content of CSR reports helps to improve analyst forecast accuracy, and this relationship is more pronounced for CSR reports with more substantial content. (shrink)

Climate change is confronting African farmers with growing uncertainties. Advances in seasonal climate predictions offer potential for assisting farmers in dealing with climate risk. Experimental cases of forecast dissemination to African rural communities suggest that participatory approaches can facilitate understanding and use of uncertain climate information. But few of these studies integrate critical reflections on participation that have emerged in the last decade which reveal how participatory approaches can miss social dynamics of power at the community level and in the (...) broader context. Furthermore, neither climate application research nor theoretical critiques of participation fully examine the culturally constructed nature of participation. Drawing on sociolinguistic analysis, in-depth interviews, and ethnographic observation, this paper examines how Ugandan farmers engage in participation in the context of discussions of seasonal climate forecasts. Forecasts were presented to farmers groups whose members were then asked to discuss the forecast among themselves. In doing so, groups sought to develop a common understanding of the forecast and consensual plans for response strategies. Focusing on one particular group meeting as an example, we show how different cultural styles of participation affect the interpretation of the forecast and the formulation of response strategies. Group interaction is shown to be mostly structured around two styles of participation. On the one hand, there is the “Western” style advocated by NGOs and the government, which centers on ensuring that all individuals who are present have opportunities to speak during discussion and to vote on group decisions. On the other hand, a “Kiganda” style of participation emphasizes the importance of affirming ties to a collectivity, respect for social hierarchy, deployment of good manners, and consensus building. The case study illuminates how the performance of different styles of participation is grounded in localized frameworks of language and culture but also draw on political and policy discourses at the national level. Although a cultural high value on consensus may work in favor of prominent members, the availability of multiple styles of participation also enables group members to exercise their agency in positive ways. Attention to the interplay of different styles of participation throws light on the subtle social processes that shape how knowledge is assessed, which sources are trusted, which and whose interpretations prevail, what options are deemed viable, how costs and benefits are calculated, and whose resources are mobilized in the effort to reduce vulnerability to climate risk. These are key questions for an assessment of the role of boundary organizations, such as farmer associations, in the communication and application of climate forecasts in agriculture. (shrink)

There are distinctive methodological and conceptual challenges in rare and severe event (RSE) forecast verification, that is, in the assessment of the quality of forecasts of rare but severe natural hazards such as avalanches, landslides or tornadoes. While some of these challenges have been discussed since the inception of the discipline in the 1880s, there is no consensus about how to assess RSE forecasts. This article offers a comprehensive and critical overview of the many different measures used to capture the (...) quality of categorical, binary RSE forecasts – forecasts of occurrence and non-occurrence – and argues that of skill scores in the literature there is only one adequate for RSE forecasting. We do so by first focusing on the relationship between accuracy and skill and showing why skill is more important than accuracy in the case of RSE forecast verification. We then motivate three adequacy constraints for a measure of skill in RSE forecasting. We argue that of skill scores in the literature only the Peirce skill score meets all three constraints. We then outline how our theoretical investigation has important practical implications for avalanche forecasting, basing our discussion on a study in avalanche forecast verification using the nearest-neighbour method (Heierli et al., 2004). Lastly, we raise what we call the “scope challenge”; this affects all forms of RSE forecasting and highlights how and why working with the right measure of skill is important not only for local binary RSE forecasts but also for the assessment of different diagnostic tests widely used in avalanche risk management and related operations, including the design of methods to assess the quality of regional multi-categorical avalanche forecasts. (shrink)

For efficient energy distribution, microgrids provide significant assistance to main grids and act as a bridge between the power generation and consumption. Renewable energy generation resources, particularly photovoltaics, are considered as a clean source of energy but are highly complex, volatile, and intermittent in nature making their forecasting challenging. Thus, a reliable, optimized, and a robust forecasting method deployed at MG objectifies these challenges by providing accurate renewable energy production forecasting and establishing a precise power generation and consumption matching (...) at MG. Furthermore, it ensures effective planning, operation, and acquisition from the main grid in the case of superior or inferior amounts of energy, respectively. Therefore, in this work, we develop an end-to-end hybrid network for automatic PV power forecasting, comprising three basic steps. Firstly, data preprocessing is performed to normalize, remove the outliers, and deal with the missing values prominently. Next, the temporal features are extracted using deep sequential modelling schemes, followed by the extraction of spatial features via convolutional neural networks. These features are then fed to fully connected layers for optimal PV power forecasting. In the third step, the proposed model is evaluated on publicly available PV power generation datasets, where its performance reveals lower error rates when compared to state-of-the-art methods. (shrink)

There is growing recognition of the need to understand societal impacts of nanotechnology. Global interest in nanotechnology implies many nations will see a need to seek out advantages for military use. Militarization will inevitably include consideration of both offensive and defensive goals. This presents emerging implications for military forces in the near future, and will greatly influence the nature of warfare and peacekeeping in the distant future. The development of nanotechnology creates possibilities for both beneficial opportunities and adverse consequences (...) as a result of application to the military strategies of both large and small nations.The promise of nanotechnology for military and security roles derives from several innate characteristics. For example, further improvements in sensors are expected and already there are numerous reports of successful developments in research and development. Material properties can be tailored on a fine scale through nanomachining, scanning force microscopy, molecular self-assembly, and other techniques. (shrink)

Hume defined ‘cause’ three times over. The two principal definitions (constant conjunction, felt determination) provide the anchors for the two main strands of the modem empiricist accounts of laws of nature 1 while the third (the counter factual definition 2) may be seen as the inspiration of the nonHumean necessitarian analyses. Corresponding to the felt determination definition is the account of laws that emphasizes human attitudes, beliefs, and actions. Latter day weavers of this strand include Nelson Goodman, A. J. (...) Ayer, and Nicholas Rescher. In Fact, Fiction and Forecast Goodman writes: “I want to emphasize the Humean idea that rather than a sentence being used for prediction because it is a law, it is called a law because it is used for prediction” (1955, p. 62). In “What is a law of nature?”, Ayer explains that the difference between ‘generalizations of fact’ and ‘generalizations of law’ “lies not so much on the side of facts which make them true, as in the attitude of those who put them forward” (1956, p. 162). And in a similar vein, Rescher maintains that lawfulness is “mind-dependent”; it is not something which is discovered but which is supplied: “Lawfulness is not found in or extracted from the evidence but superadded to it. Lawfulness is a matter of imputation” (1970, p. 107). By contrast, the constant conjunction definition promotes the view that laws are to be analyzed in terms of the de re characteristics of regularities, independently of the attitudes and actions of actual or potential knowers. (shrink)

Arrivé à un stade de ma vie qui m'engage à prendre du recul, je voudrais témoigner dans ce livre d'un certain sentiment de spiritualité, qui a émergé de mes recherches pour comprendre l'ordre caché des choses et le sens secret de la nature. Ce sentiment est né d'un émerveillement et d'une révélation sur la simplicité des codes naturels qui conduisent au jaillissement, dans l'espace et dans le temps, de formes d'une extrême diversité et d'une grande beauté. Une morphogenèse qui (...) a passionné des penseurs comme Pythagore, Benoît Mandelbrot ou Alan Turing, et qui se poursuit par le travail et l'oeuvre des hommes. Ce travail est désormais mis en cause par les extensions du corps et du cerveau humains que représentent l'intelligence artificielle et les robots... Aujourd'hui, il devient plus difficile de prédire les évolutions exponentielles auxquelles nous sommes confrontés dans les domaines scientifique, technologique, économique et politique. Mon message vise à alerter les prospectivistes, les politiques, les économistes, les scientifiques, non seulement sur la vitesse de ces évolutions, mais surtout sur les interdépendances émergentes entre intelligence artificielle, robotique, travail humain et modifications de l'" ADN " d'Internet. Mal comprises, ces évolutions peuvent engendrer des mouvements tels que le transhumanisme. Mieux intégrées à nos réflexions, elles peuvent en revanche mener à une nouvelle étape de l'évolution de l'humanité... (shrink)

Air temperature prediction can play a significant role in studies related to climate change, radiation and heat flux estimation, and weather forecasting. This study applied and compared the outcomes of three advanced fuzzy inference models, i.e., dynamic evolving neural-fuzzy inference system, hybrid neural-fuzzy inference system, and adaptive neurofuzzy inference system for AT prediction. Modelling was done for three stations in North Dakota, USA, i.e., Robinson, Ada, and Hillsboro. The results reveal that FIS type models are well suited when handling highly (...) variable data, such as AT, which shows a high positive correlation with average daily dew point, total solar radiation, and negative correlation with average wind speed. At the Robinson station, DENFIS performed the best with a coefficient of determination of 0.96 and a modified index of agreement of 0.92, followed by ANFIS with R2 of 0.94 and md of 0.89, and HyFIS with R2 of 0.90 and md of 0.84. A similar result was observed for the other two stations, i.e., Ada and Hillsboro stations where DENFIS performed the best with R2: 0.953/0.960, md: 0.903/0.912, then ANFIS with R2: 0.943/0.942, md: 0.888/0.890, and HyFIS with R2: 0.908/0.905, md: 0.845/0.821, respectively. It can be concluded that all three models are capable of predicting AT with high efficiency by only using DP, TSR, and WS as input variables. This makes the application of these models more reliable for a meteorological variable with the need for the least number of input variables. The study can be valuable for the areas where the climatological and seasonal variations are studied and will allow providing excellent prediction results with the least error margin and without a huge expenditure. (shrink)

This paper investigates if and to what point it is possible to trade on news sentiment and if deep learning, given the current hype on the topic, would be a good tool to do so. DL is built explicitly for dealing with significant amounts of data and performing complex tasks where automatic learning is a necessity. Thanks to its promise to detect complex patterns in a dataset, it may be appealing to those investors that are looking to improve their trading (...) process. Moreover, DL and specifically LSTM seem a good pick from a linguistic perspective too, given its ability to “remember” previous words in a sentence. After having explained how DL models are built, we will use this tool for forecasting the market sentiment using news headlines. The prediction is based on the Dow Jones industrial average by analyzing 25 daily news headlines available between 2008 and 2016, which will then be extended up to 2020. The result will be the indicator used for developing an algorithmic trading strategy. The analysis will be performed on two specific cases that will be pursued over five time-steps and the testing will be developed in real-world scenarios. (shrink)