A key theme in capital markets research examines the relationships between accounting information and firm value. Two concerns relating to the value relevance of accounting information are: (1) concerns over the explanatory and predictive power of the evidence presented in the prior literature (Lev, 1989); and (2) the evidence of a deterioration in the association between accounting information and stock prices over the past four decades (Collins, Maydew and Weiss, 1997; Francis and Schipper, 1999; Lev and Zarowin, 1999). These concerns provide the key motivation for this thesis which examines: (1) the usefulness of the clean surplus accounting equation in valuation; (2) the role of accounting information in estimating and predicting systematic risk and; (3) the changing nature of the relationship between accounting information, stock prices and risk over time. The empirical research provides evidence of the value-irrelevance of the clean surplus equation and that controlling for the functional form of the earnings-returns relationship is more important. Evidence is also provided that accounting variables are highly associated with M-GARCH risk betas and also possess predictive ability relative to these risk measures. Finally, the relationships between stock prices, risk models and accounting information are shown to have not deteriorated over time, contrary to prior evidence. Rather, the functional form of the relationship has changed from linear to a non-linear arctan association. Overall, accounting information continues to play the central role in the determination of stock prices and risk metrics.

abstract: Time series forecasting is the prediction of future data after analyzing the past data for temporal trends. This work investigates two fields of time series forecasting in the form of Stock Data Prediction and the Opioid Incident Prediction. In this thesis, the Stock Data Prediction Problem investigates methods which could predict the trends in the NYSE and NASDAQ stock markets for ten different companies, nine of which are part of the Dow Jones Industrial Average (DJIA). A novel deep learning model which uses a Generative Adversarial Network (GAN) is used to predict future data and the results are compared with the existing regression techniques like Linear, Huber, and Ridge regression and neural network models such as Long-Short Term Memory (LSTMs) models. In this thesis, the Opioid Incident Prediction Problem investigates methods which could predict the location of future opioid overdose incidences using the past opioid overdose incidences data. A similar deep learning model is used to predict the location of the future overdose incidences given the two datasets of the past incidences (Connecticut and Cincinnati Opioid incidence datasets) and compared with the existing neural network models such as Convolution LSTMs, Attention-based Convolution LSTMs, and Encoder-Decoder frameworks. Experimental results on the above-mentioned datasets for both the problems show the superiority of the proposed architectures over the standard statistical models. / Dissertation/Thesis / Masters Thesis Computer Science 2019

Background: Predicting stock prices in today’s complex financial landscape is asignificant challenge. An innovative approach to address this challenge is integrating sentiment analysis techniques with the well-established Autoregressive IntegratedMoving Average (ARIMA) model. Modern financial markets are influenced by various factors, including real-time news and social media trends, which demand accuratepredictions. This research recognizes the growing importance of market sentiment derived from news and aims to improve stock price prediction by combining ARIMA’sanalytical capabilities with sentiment analysis. This endeavor seeks to provide aclearer understanding of the intricate dynamics of stock price movements in an eramarked by abundant information and rapidly changing market conditions. The integration of these methods has the potential to enhance the accuracy of stock priceforecasts, offering benefits to investors and financial analysts alike. Objectives: The project involves three key components. It begins by gatheringhistorical stock data for a specific stock ticker and conducting essential data preprocessing. Next, it focuses on extracting news headlines from a prominent financial website and conducting a thorough sentiment analysis of these headlines. Thissentiment analysis provides valuable insights into public sentiment surrounding thechosen stocks, with visualizations representing positive, negative, and neutral trends.Finally, the project aims to combine the findings from both components using an Ensemble Method, resulting in a comprehensive suggestion to user whether to buy,holdor sell the stock. These components collectively aim to improve stock price predictions and assess the adaptability of the ARIMA model to changing market conditionsalong the time and significant events. Methods: This project explores an innovative approach to improve stock pricepredictions, combining the ARIMA model with sentiment analysis methods usingfinancial news data. The study involved collecting historical stock data from YahooFinance, employing moving averages like 5-day, 30-day and 90-day windows, andusing advanced models such as ARIMA for predictions. Our analysis also includestime series plots at various intervals, providing valuable perspectives. Through theEnsemble Method, which integrates quantitative predictions and sentiment analysis,we generated practical recommendations for a five-day forecast. Our work addressedgaps in integrating sentiment analysis into stock prediction models and adapting tochanging market conditions, contributing to the advancement of stock forecastingmethodologies. Results: The ensembled predictive model for stock prices demonstrates favorableoutcomes. The Mean Absolute Error (MAE) is 0.8659, indicating accuracy, and theRoot Mean Squared Error (RMSE) is 0.1732, showing the overall prediction error.The Mean Absolute Percentage Error (MAPE) is 1.8541, suggesting precision in comparison to actual stock prices. The R-squared value is 0.9804, indicating the model’sability to explain variation in stock price data. These findings highlight the model’seffectiveness in providing reliable insights for investors in the dynamic stock market. Conclusions: The analysis with the ARIMA model to enhance stock price predictions. It revealed that sentiment analysis complements traditional methods, providing valuable insights for decision-making. Evaluating ARIMA’s long-term performance suggests adaptable forecasting techniques. This work contributes to advancingfinancial analysis and improving stock price predictions.

As the world is gravitating toward an information economy, it has become more and more critical for an investor to understand the impact of data and information. One of the sources of data that can be converted into information are texts from microblogging platforms, such as Twitter. The user of such a microblogging account can filtrate opinion and information to millions of people. Depending on the account holder, the opinion or information originated from the designated account may lead to different societal impact. The microblogging scope of this investigation are politicians holding a Twitter account. This investigation will look into the relationship between political tweets' sentiment and market movement and the subsequent longevity of such an effect. The classified sentiments are positive or negative. The presence of artificial intelligence is vital for a data-driven investigation; in the context of this investigation, artificial intelligence will be used to classify the sentiment of the political tweet. The methods chose to assess the impact of a political tweet and market movement is event-study. The impact is expressed in either a positive or a negative cumulative abnormal return subsequent to the political tweet. The findings of the investigation indicate that on average, there is no statistical evidence that a political tweets' sentiment leads to an abnormal return. However, in specific cases, political tweet leads to abnormal return. Moreover, it has been determined that the longevity of the effect is rather short. This is an interdisciplinary approach that can be applied by individual and institutional investors and financial institutions.

Being able to predict stock prices might be the unspoken wish of stock investors. Although stock prices are complicated to predict, there are many theories about what affects their movements, including interest rates, news and social media. With the help of Machine Learning, complex patterns in data can be identified beyond the human intellect. In this thesis, a Machine Learning model for time series forecasting is created and tested to predict stock prices. The model is based on a neural network with several layers of Long Short-Term Memory (LSTM) and fully connected layers. It is trained with historical stock values, technical indicators and Twitter attribute information retrieved, extracted and calculated from posts on the social media platform Twitter. These attributes are sentiment score, favourites, followers, retweets and if an account is verified. To collect data from Twitter, Twitter’s API is used. Sentiment analysis is conducted with Valence Aware Dictionary and sEntiment Reasoner (VADER). The results show that by adding more Twitter attributes, the Mean Squared Error (MSE) between the predicted prices and the actual prices improved by 3%. With technical analysis taken into account, MSE decreases from 0.1617 to 0.1437, which is an improvement of around 11%. The restrictions of this study include that the selected stock has to be publicly listed on the stock market and popular on Twitter and among individual investors. Besides, the stock markets’ opening hours differ from Twitter, which constantly available. It may therefore introduce noises in the model. / Att kunna förutspå aktiekurser kan sägas vara aktiespararnas outtalade önskan. Även om aktievärden är komplicerade att förutspå finns det många teorier om vad som påverkar dess rörelser, bland annat räntor, nyheter och sociala medier. Med hjälp av maskininlärning kan mönster i data identifieras bortom människans intellekt. I detta examensarbete skapas och testas en modell inom maskininlärning i syfte att beräkna framtida aktiepriser. Modellen baseras på ett neuralt nätverk med flera lager av LSTM och fullt kopplade lager. Den tränas med historiska aktievärden, tekniska indikatorer och Twitter-attributinformation. De är hämtad, extraherad och beräknad från inlägg på den sociala plattformen Twitter. Dessa attribut är sentiment-värde, antal favorit-markeringar, följare, retweets och om kontot är verifierat. För att samla in data från Twitter används Twitters API och sentimentanalys genomförs genom VADER. Resultatet visar att genom att lägga till fler Twitter attribut förbättrade MSE mellan de förutspådda värdena och de faktiska värdena med 3%. Genom att ta teknisk analys i beaktande minskar MSE från 0,1617 till 0,1437, vilket är en förbättring på 11%. Begränsningar i denna studie innefattar bland annat att den utvalda aktien ska vara publikt listad på börsen och populär på Twitter och bland småspararna. Dessutom skiljer sig aktiemarknadens öppettider från Twitter då den är ständigt tillgänglig. Detta kan då introducera brus i modellen.

面對市場未來趨勢的不確定性，投資者可以運用「投資組合保險」的概念，既能保障原本所投資的資產價值，又可以參與市場上漲時的獲利。本研究以類神經網路來研究證券市場的現象，一方面是已經有許多類神經網路在財務分析上的研究成果，另一方面是其具有學習以及預測的能力。 本研究首先探討投資組合保險策略，接著再比較投資組合保險策略在不同市況下的績效表現，隨後提出兩個階段的研究架構，經過設計與建置，以類神經網路模型進行對大盤未來漲跌型態的模擬預測，並利用預測的結果，輔助投資組合保險策略的決策，最後並將研究結果與大盤績效做綜合分析比較。 本研究的資料採取自台灣證券集中交易市場，期間為1991年1月3日至2002年12月31日，共3306個交易日，取大盤每日交易之歷史資料，經過處理後建立資料庫。類神經網路模型具有預測未來大盤漲跌區間的能力，在本研究所提出的漲跌區間劃分方式上，其預測正確率達到55%，預測的結果與實際漲跌完全相反的比例僅10%，其餘的35%為相鄰區間的預測誤差，其預測能力有助於投資組合保險策略的進行。 經過類神經網路模型輔助而進行的停損策略（SL），其年報酬率以及Sharpe Ratio，在大盤下跌的期間，兩個績效指標衡量結果皆為正值（21.125%＞0以及980.493＞0），充分發揮保險功能；而在大盤上漲的期間，兩個績效指標衡量結果皆優於大盤（46.544%＞17.137%以及393.808＞110.069）。 在年報酬率與Sharpe Ratio之間，本研究主張在探討投資組合保險時應著重風險的衡量，因此經過類神經網路模型輔助而進行的固定比例投資組合策略（CPPI），搭配槓桿乘數M值的調整，在大盤下跌的期間，其Sharpe Ratio依然可以維持正值，達到保險的效果，保護投資人的資產免於損失；而在大盤上漲的期間，其Sharpe Ratio更是高於大盤，可以享受資產價值提昇的獲利。 / Facing the uncertainty of the market trend, an investor can use the concept of “ Portfolio Insurance ” to protect the value of his portfolio in bear market and earn the benefit from bull market. There have been many researches about applying Neural Network in the financial analysis and Neural Network has the abilities to learn and forecast. This research evaluates the performances of the portfolio insurance strategies in different market trends. Then two-stage research structure has been designed and built. The first stage is forecasting the up-and-down trends of the equity market index by Neural network model. The second stage is using the forecasted results assisting the portfolio insurance decisions. Finally, the results of this research have been analyzed and compared with the benchmark. The Neural Network is able to forecast the future up-and-down trends. The accurate rate is 55%. During the bear market（2002）, the annual rate of return and Sharpe Ratio of the stop loss（SL） strategy which is assisted by NN are both positive（21.125%＞0 and 980.493＞0）. During the bull market（2001）, they both outperform the benchmark（46.544%＞17.137% and 393.808＞110.069）. The annual rate of return is more important than Sharpe Ratio because the risk measurement is an important factor in portfolio insurance strategy. Sharpe Ratios of the CPPI strategy which is assisted by NN outperform the benchmark in both above mentioned bear and bull market. In short, the SL and CPPI strategy assisted by NN not only protect the value of the portfolio from losing in bear market but also gain profit in bull market, so they are the ideal portfolio insurance strategies.

Machine learning is an area of computer science that only grows as time goes on, and there are applications in areas such as finance, biology, and computer vision. Some common applications are stock price prediction, data analysis of DNA expressions, and optical character recognition. This thesis uses machine learning techniques to predict prices for different stocks and indices on the Swedish stock market. These techniques are then compared to see which performs best and why. To accomplish this, we used some of the most popular models with sets of historical stock and index data. Our best-performing models are linear regression and neural networks, this is because they are the best at handling the big spikes in price action that occur in certain cases. However, all models are affected by overfitting, indicating that feature selection and hyperparameter optimization could be improved.

Parametric models are used to understand dynamical systems and predict its future behavior. It is difficult to estimate the model’s parametric values since there are usually many parameters and they are highly correlated. The aim of this project is to apply the method of indirect inference and the two stage approach to estimate the drift and volatility parameters of a Geometric Brownian Motion. This was first done by estimating the parameters of a known Geometric Brownian process. Then, the Coca-Cola Company’s stock was used for a five-year forecast to study the estimators’ predictive power. The two stage approach struggles when the data does not truly follow a Geometric Brownian Motion, but when it does it produces highly efficient and accurate estimates. The method of indirect inference produces better estimates, than the two stage approach,for data that deviates from a Geometric Brownian Motion.Therefore, it is preferable to use indirect inference over two stage approach for stock price forecasting. / Parametriska modeller används för attförstå dynamiska system och förutspå dess framtida beteende.Det är utmanande att skatta modellens parametriska värdeneftersom det vanligtvis finns många parametrar och de är oftastarkt korrelerade. Målet med detta projekt är att tillämpametoderna indirect inference och two stage approach för attskatta drivnings- och volatilitetsparametrarna av en geometriskBrownsk rörelse. Först skattades parametrarna av en kändGeometrisk Brownsk rörelse. Sedan användes The Coca-ColaCompanys aktie i syfte att studera estimatorernas förmåga attförutspå en femårig period. Two stage approach fungerar dåligtför data som inte helt följer en geometrisk Brownsk rörelse, mennär datan gör det är skattningarna noggranna och effektiva.Indirect inference ger bättre skattningar än two stage approachnär datan inte helt följer en geometrisk Brownsk rörelse. Därförär indirect inference att föredra för aktieprognoser. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

This report assesses different machine learning models’accuracies to predict whether a stock will go up or down invalue in a short term. The models that is used is linear regression,LSTM and Elman RNN. These models was trained on historicalprice data from the Nasdaq Stock Exchange. The idea that thereexist a relationship of the price movement of a stock and its futurevalue is called ’techncial analysis’. The result shows that neitherLSTM nor Elman RNN provides any statistical significance ofits accuracy for any of the implementations. Linear regression,provides a significant accuracy for longer time series predictionof the price when trained on 100 days of data and prediction ofits movement after five more days. / I denna report undersöks olika maskininlärningsmodeller noggrannhet för att förutspå om en aktie kommer att gå upp eller ner i värde på kort sikt. De evaluerade maskininlärningsmodellernamodellerna är följande: linjär regression, LSTM och Elman RNN. Dessa modeller tränades med hjälp av historisk prisdata från Nasdaq Stock Exchange. Ide´en om att det finns ett samband mellan prisrörelsen av en aktie och dess kortsiktiga framtida värde är benämnt som ’teknisk analys’. Resultaten visar att varken LSTM eller Elman RNN förmedlar en noggrannhet med statistisk signifikans för någon av de anänvda implementationerna. Linjär regression förmedlar en statistisk signikant noggrannhet för längre tidserie förutsägelser med träningsdata om 100 dagar och förutsägelse av aktiens rörelse efter fem fler dagar. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

股價的漲跌變化是由於證券市場中眾多不同投資人及其投資決策後所產生的結果。然而，影響股價變動的因素眾多且複雜，新聞也屬於其中一種，新聞事件不但是投資人用來得知該股票上市公司的相關營運資訊的主要媒介，同時也是影響投資人決定或變更其股票投資策略的主要因素之一。本研究提出以新聞文件做為股價漲跌預測系統的基礎架構，透過文字探勘技術及分類技術來建置出能預測當日個股收盤股價漲跌趨勢之系統。 本研究共提出三種分類模型，分別是簡易貝氏模型、k最近鄰居模型以及混合模型，並設計了三組實驗，分別是分類器效能的比較、新聞樣本資料深度的比較、以及新聞樣本資料廣度的比較來檢驗系統的預測效能。實驗結果顯示，本研究所提出的分類模型可以有效改善相關研究中整體正確率高但各個類別的預測效能卻差異甚大的情況。而對於影響投資人獲利與否的關鍵類別"漲"及類別"跌"的平均預測效能上，本研究所提出的這三種分類模型亦同時具有良好的成效，可以做為投資人進行投資決策時的有效參考依據。 / Stocks' closing price levels can provide hints about investors' aggregate demands and aggregate supplies in the stock trading markets. If the level of a stock's closing price is higher than its previous closing price, it indicates that the aggregate demand is stronger than the aggregate supply in this trading day. Otherwise, the aggregate demand is weaker than the aggregate supply. It would be profitable if we can predict the individual stock's closing price level. For example, in case that one stock's current price is lower than its previous closing price. We can do the proper strategies(buy or sell) to gain profit if we can predict the stock's closing price level correctly in advance. In this thesis, we propose and evaluate three models for predicting individual stock's closing price in the Taiwan stock market. These models include a naïve Bayes model, a k-nearest neighbors model, and a hybrid model. Experimental results show the proposed methods perform better than the NewsCATS system for the "UP" and "DOWN" categories.