This report discusses a multi-stage stochastic programming model that maximizes expected ending time profit assuming investors can forecast a bull or bear market trend. If an investor can always predict the market trend correctly and pick the optimal stochastic strategy that matches the real market trend, intuitively his return will beat the market performance. For investors with different levels of prediction accuracy, our analytical results support their decision of selecting the highest return strategy. Real stock prices of 154 stocks on 73 trading days are collected. The computational results verify that accurate prediction helps to exceed market return while portfolio profit drops if investors partially predict or forecast incorrectly part of the time. A sensitivity analysis shows how risk control requirements affect the investor's decision on selecting stochastic strategies under the same prediction accuracy. / text

This thesis analyzes the impact of political risk for investment decision-ing-on invest-ments into large investment projects. The failure of investors in the field of large in-vestment projects is the vast majority caused by the politic-social grounds, whose quan-tification is extremely difficult. Political risk affects economic conditions and the stabil-ity of the environment, therefore knowledge of its development is essential for the prop-er investment decisions. His predictions are quantitative level problematic. The method used qualitative modeling falls within the field of artificial intelligence and used to model the trend. The work describes the process of creating qualitative model, its inter-pretation and recommendations for use in investment decisions.

Stock market plays an important role in the modern capital market. As a result, the prediction of financial assets attracts people in different areas. Moreover, it is commonly accepted that stock price movement generally follows a major trend. As a result, forecasting the market trend becomes an important mission for a prediction method. Accordingly, we will predict the long term trend rather than the movement of near future or change in a trading day as the target of our predicting approach. Although there are various kinds of analyses for trend prediction, most of them use clear cuts or certain thresholds to classify the trends. Users (or investors) are not informed with the degrees of confidence associated with the recommendation or the trading signal. Therefore, in this research, we would like to study an approach that could offer the confidence of the trend analysis by providing the probabilities of each possible state given its historical data through Dynamic Bayesian Network. We will incorporate the well-known principles of Dow¡¦s Theory to better model the trend of stock movements. Through the results of our experiment, we may say that the financial performance of the proposed model is able to defeat the buy and hold trading strategy when the time scope covers the entire cycle of a trend. It also means that for the long term investors, our approach has high potential to win the excess return. At the same time, the trading frequency and correspondently trading costs can be reduced significantly.

Trend prediction has become an extremely popular practice in many industrial sectors and academia. It is beneficial for strategic planning and decision making, and facilitates exploring new research directions that are not yet matured. To anticipate future trends in academic environment, a researcher needs to analyze an extensive amount of literature and scientific publications, and gain expertise in the particular research domain. This approach is time-consuming and extremely complicated due to abundance of data and its diversity. Modern machine learning tools, on the other hand, are capable of processing tremendous volumes of data, reaching the real-time human-level performance for various applications. Achieving high performance in unsupervised prediction of emerging trends in text can indicate promising directions for future research and potentially lead to breakthrough discoveries in any field of science. This thesis addresses the problem of emerging trend prediction in text in two main steps: it utilizes HDP topic model to represent latent topic space of a given temporal collection of documents, DBSCAN clustering algorithm to detect groups with high-density regions in the document space potentially leading to emerging trends, and applies KLdivergence in order to capture deviating text which might indicate birth of a new not-yet-seen phenomenon. In order to empirically evaluate the effectiveness of the proposed framework and estimate its predictive capability, both synthetically generated corpora and real-world text collections from arXiv.org, an open-access electronic archive of scientific publications (category: Computer Science), and NIPS publications are used. For synthetic data, a text generator is designed which provides ground truth to evaluate the performance of anomaly detection algorithms. This work contributes to the body of knowledge in the area of emerging trend prediction in several ways. First of all, the method of incorporating topic modeling and anomaly detection algorithms for emerging trend prediction is a novel approach and highlights new perspectives in the subject area. Secondly, the three-level word-document-topic topology of anomalies is formalized in order to detect anomalies in temporal text collections which might lead to emerging trends. Finally, a framework for unsupervised detection of early signals of emerging trends in text is designed. The framework captures new vocabulary, documents with deviating word/topic distribution, and drifts in latent topic space as three main indicators of a novel phenomenon to occur, in accordance with the three-level topology of anomalies. The framework is not limited by particular sources of data and can be applied to any temporal text collections in combination with any online methods for soft clustering.

在網際網路快速發展下，大量使用者在獲取知識與新聞的管道，已由傳統媒體轉移到網路上。網路活動下使用者互動後所留下的訊息，也就是網路口碑，也逐漸受到重視。而隨著經濟發展，國人在固定薪資下無法負擔高房價、高物價的生活，如何透過投資理財來增加自身財富，已是非常普遍，其中又以股市投資為大眾所重視之途徑。 網路新聞的發布，除了具有網路的即時性外，配合使用者閱讀內化後所留下的評論，應含有比網路新聞本身內容更多的資訊，投資者便可藉此找尋隱含之中大量市場消息與資訊。 本研究為了在龐大的資料量中，幫助使用者挖掘其背後之涵義，進而提供投資預測，將蒐集網路新聞及其閱讀者評論共1068篇，並分為訓練資料與測試資料，使用文字探勘及相關技術做前處理，再透過kNN分群技術，計算訓練資料文件間相似度，將大量未知資料依其相似度做分群後，利用歷史股價訊息對群集結果之特徵分析解釋之並建立預測模型，最後透過測試資料將模型分群結果進行評估，進而對股價趨勢做出預測。 / With the rapid development of the Internet, the way of user access to knowledge and news transfer from traditional media to the network. Internet word-of-mouth, the message generated from users' interaction on internet, attracts more and more people's attention. With economic development, people in the fixed salary cannot afford high prices and high price in live. People increase their own wealth through investment is very common, among which the stock market is the way to public attention. Internet news has the immediacy of the Internet. And the comments left with the user to read the internalization should contain more information than the Internet news. Investors can find the market news and information by Internet news and comments. In this study, in order to help the user to find the meaning behind the huge amount of data, and thus provide investment forecast. We will collect 1068 of internet news and reader reviews to divide into training data and test data using text mining and related technologies to do the pre-treatment, and then calculate the similarity between the training data by kNN, a lot of unknown data according to their similarity clustering. Cluster through the historical share price analysis and modeling. Finally, the model clustering results were evaluated through the test data to predict price trends. The prediction model from training data clustering, use test data to do the evaluation found: k = 15, the similarity threshold value = 0.05, cluster the results of the F-measure performance up to 56% rise in the cluster. K values and the similarity threshold will be adjusted to obtain the most favorable results of the model

[EN] The object of this study is the design of a cybermetric methodology whose objectives are to measure the success of the content published in an online media and the possible prediction of the selected success variables. Framed in the field of digital journalism, it responds to the need to analyze the success of web content so that it can help in the decision-making of the editorial team of a digital medium. A line of research focused on the content itself, providing an innovative vision to that of previous research, and a methodology that serves as a basis for future scientific advances. It is about the contribution of valuable information, either from the statistical analysis of the data or from the possible prediction of the success indicators of greatest interest to the environment. In this way, it could be integrated as a feedback into the content strategy and thus favor its iterative optimization. The main objective, therefore, is the design of a cybermetric methodology for calculating the success of an online publication, having as specific objectives: to research the concept of success in digital journalism, the social network Twitter, web analytics and web advertising; design the methodology and determine what tools and reports are needed; extract and process data for statistical analysis; perform regressions that allow to obtain prediction equations of the selected success variables; and validate the prediction equations with test data and obtain their precision, serving this as a degree of confidence in the prediction. The design of the methodology has served to observe a significant over-dispersion in the data, as well as to demonstrate that the success of a web content has a strongly multifactorial nature, which causes a decrease in the variability calculated using the indicators proposed by previous research. This thesis serves, then, as the basis for a very interesting research framework both at an academic and business level: the prediction of the success of digital content. / [ES] El objetivo de estudio es el diseño de una metodología cibermétrica para medir el éxito de los contenidos publicados en un medio de comunicación online y su posible predicción, de manera que se pueda orientar la optimización de los futuros contenidos publicados por el medio. Enmarcada en el ámbito del periodismo digital, responde a la necesidad de analizar el éxito de los contenidos web de manera que se pueda ayudar en la toma de decisiones del equipo editorial. Para ello, se ha realizado un extenso estudio de las publicaciones académicas versadas en las diferentes disciplinas que tienen lugar en esta tesis: la comunicación de contenidos digitales, Twitter, la difusión de las noticias en Twitter, la analítica web, la cibermetría, la analítica en Twitter, el análisis de tendencias en Twitter y la publicidad web. Con dicho marco, se ha obtenido información valiosa para la optimización futura de los contenidos digitales, ya sea procedente del análisis estadístico de los datos o de la posible predicción de los indicadores de éxito de mayor interés para el medio. De esta manera, se podría integrar de manera retroalimentada en la estrategia de contenidos y favorecer así su optimización iterativamente. Para ello, se han tenido en cuenta los siguientes objetivos específicos: investigar el concepto de éxito en el periodismo digital, la red social Twitter, la analítica web y la publicidad en la web; diseñar la metodología y determinar qué herramientas y reportes son necesarios; extraer y procesar los datos para su análisis estadístico; realizar regresiones que permitan obtener ecuaciones de predicción de las variables de éxito seleccionadas; y validar las ecuaciones de predicción con datos de test y obtener su precisión, sirviendo esta como grado de confianza en la predicción. El diseño de la metodología ha servido para observar una sobre dispersión significativa en los datos, así como demostrar que el éxito de un contenido web tiene un carácter fuertemente multifactorial, lo cual provoca una disminución en la variabilidad calculada mediante los indicadores propuestos por investigaciones previas. Esta tesis sirve, entonces, como base para una línea de investigación sobre la optimización de contenido digital basándose en la predicción estadística de su éxito. / [CAT] L'objectiu d'estudi és el disseny d'una metodologia cibermètrica per a mesurar l'èxit dels continguts publicats en un mitjà de comunicació en línia i la seua possible predicció, de manera que es puga orientar l'optimització dels futurs continguts publicats pel mitjà. Emmarcada en l'àmbit del periodisme digital, respon a la necessitat d'analitzar l'èxit dels continguts web de manera que es puga ajudar en la presa de decisions de l'equip editorial. Per a això, s'ha realitzat un extens estudi de les publicacions acadèmiques versades en les diferents disciplines que tenen lloc en aquesta tesi: la comunicació de continguts digitals, Twitter, la difusió de les notícies en Twitter, l'analítica web, la cibermetría, l'analítica en Twitter, l'anàlisi de tendències en Twitter i la publicitat web. Amb aquest marc, s'ha obtingut informació valuosa per a l'optimització futura dels continguts digitals, ja siga procedent de l'anàlisi estadística de les dades o de la possible predicció dels indicadors d'èxit de major interés per al mitjà. D'aquesta manera, es podria integrar de manera retroalimentada en l'estratègia de continguts i afavorir així la seua optimització iterativament. Per a això, s'han tingut en compte els següents objectius específics: investigar el concepte d'èxit en el periodisme digital, la xarxa social Twitter, l'analítica web i la publicitat en la web; dissenyar la metodologia i determinar quines eines i reportes són necessaris; extraure i processar les dades per a la seua anàlisi estadística; realitzar regressions que permeten obtindre equacions de predicció de les variables d'èxit seleccionades; i validar les equacions de predicció amb dades de test i obtindre la seua precisió, servint aquesta com a grau de confiança en la predicció. El disseny de la metodologia ha servit per a observar una sobre dispersió significativa en les dades, així com demostrar que l'èxit d'un contingut web té un caràcter fortament multifactorial, la qual cosa provoca una disminució en la variabilitat calculada mitjançant els indicadors proposats per investigacions prèvies. Aquesta tesi serveix, llavors, com a base per a una línia d'investigació sobre l'optimització de contingut digital basant-se en la predicció estadística del seu èxit. / Yeste Moreno, VM. (2021). Diseño de una metodología cibermétrica de cálculo del éxito para la optimización de contenidos web [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/176009 / TESIS