Background. Stock market prediction is an active yet challenging research area. A lot of effort has been put in by both academia and practitioners to produce accurate stock market predictions models, in the attempt to maximize investment objectives. Tree-based ensemble machine learning methods such as XGBoost have proven successful in practice. At the same time, there is a growing trend to incorporate multiple data sources in prediction models, such as historical prices and text, in order to achieve superior forecasting performance. However, most applications and research have so far focused on the American or Asian stock markets, while the Swedish stock market has not been studied extensively from the perspective of hybrid models using both price and text derived features.  Objectives. The purpose of this thesis is to investigate whether augmenting a numerical dataset based on historical prices with sentiment features extracted from financial news improves classification performance when predicting the daily price trend of the Swedish stock market index, OMXS30. Methods. A dataset of 3,517 samples between 2006 - 2020 was collected from two sources, historical prices and financial news. XGBoost was used as classifier and four different metrics were employed for model performance comparison given three complementary datasets: the dataset which contains only the sentiment feature, the dataset with only price-derived features and finally, the dataset augmented with sentiment feature extracted from financial news.  Results. Results show that XGBoost has a good performance in classifying the daily trend of OMXS30 given historical price features, achieving an accuracy of 73% on the test set. A small improvement across all metrics is recorded on the test set when augmenting the numerical dataset with sentiment features extracted from financial news.  Conclusions. XGBoost is a powerful ensemble method for stock market prediction, reflected in a satisfactory classification performance of the daily movement direction of OMXS30. However, augmenting the numerical input set with sentiment features extracted from text did not have a powerful impact on classification performance in this case, as the improvements across all employed metrics were small.

Aim: This study aims to examine whether highly ranked companies in sustainability generate a higher return then companies operating in controversial industries in the swedish market during the years 2015-2019.  Method: This study examines return and if connections exist whether the companies apply sustainability thinking or controversial industry. To investigate correlations this study uses a quantitative method thru using regression analysis with data obtained from the years2015-2019 in the swedish market. The study has formed a null hypothesis and an alternative hypothesis to test collected secondary data. The study is based on a deductive approach.Totally 32 companies are included in this study and the collected secondary data comes från Nasdaq and the companies own annual reports. The return is the studies dependent variable and P/E ratios, the standard deviation and ROA are used as control variables in this study.  Result and conclusion: The studies conclusion is that the result is insignificant, thesustainable companies nor the controversial companies performs better according to this studies data and analysis. The study’s regressions show no difference in returns between the studied controversial companies and the sustainable companies. The result shows neither positive nor negative relationships and therefore the study’s alternative hypothesis is rejected. / Syfte: Syftet med denna studie är att undersöka ett urval av hållbara företag eller kontroversiella företag presterar en bättre avkastning på den svenska marknaden under perioden 2015-2019. Studien grundar sig på att reda ut om en hållbar investering kan ge en förklaring till investeringens avkastning.  Metod: Studien har utifrån litteraturgenomgången format en nollhypotes och alternativhypotes som har prövats med hjälp av tillämpad sekundär data. Insamlingen av den sekundära datan som studien tillämpat har byggts på en deduktiv ansats. Urvalet resulterade i att 32 företag stycken företag har undersökts. Sekundärdatan har hämtats från Nasdaq och företagens årsredovisningar. Avkastningen är använd som beroende variabeln, hållbara företag som den oberoende och P/E-tal, standardavvikelsen och ROA är studiens kontrollvariabler. Detta har testats med hjälp statiska regressionsanalyser. Resultat & slutsats: Resultatet från regressions analyserna visade att inget signifikant samband inte kunde påvisas. Vilket betyder inget signifikant samband mellan hållbarhet och avkastning. Vi kunde inte se någon skillnad i avkastning mellan de studerade kontroversiella företagen och de hållbara företagen. Resultatet visar inte att sambandet är negativt eller positivt och studiens alternativ hypotes förkastas.

Each individual is both a consumer and an investor in the market. It is the common goal of every investor to achieve a high return on investment through the portfolio of profit maximization. As a result, the ratio of assets in a portfolio has become a hot topic. In China, real estate and the stock market are two main markets favoured by both individual and institutional investors. And there is a significant economic link between the two markets. Therefore, their mutual relationship and long-term and short-term causality can provide good guidance for investors. This paper studies the causality and correlation between stock trading volume and real estate trading volume in 31 provinces of mainland China. The empirical results in this paper is based on a panel data from 2000 to 2016 and divides 31 provinces into three different economic regions. The panel unit root test and the Pedroni co-integration test were carried out. The Hausman test was used to select among different estimation methods. Panel Mean Group is found the most suitable analysis method. It is found that the main industries in different provinces may affect the short-term causal relationship between real estate and the stock market. But in the long run, the causal relationship between real estate and the stock market is two-way and stable.

Background: The credit rating agencies have been heavily contested and criticized. In addition to this, other informational sources may potentially deliver the information that the CRA is intended to provide. This may have changed their role in reducing information asymmetry in the financial market. Purpose: This thesis will investigate (i) whether changes (upgrade/downgrade) in credit ratings lead to abnormal returns in share value, and thereby provide useful information to potential and current investors. The thesis will also (ii) examine whether there are significant differences between the periods before and after the GFC in 2008. Method: Regression based event study using a dummy-variable approach. Conclusions: No strong evidence that credit ratings have a significant effect on stock prices in the European stock market. Small indications that the market is responding more strongly to a rating change announcement during the period 2000-2008 compared to 2009-2019.

Prior studies on the impact of the termination of overfunded defined benefit pension plans on shareholders' wealth have produced conflicting findings. The first study on the stock market reaction to pension plan termination was conducted by Alderson and Chen (1986); this study claimed that shareholders realize significant positive abnormal returns around the termination announcement date. A more recent study, by Moore and Pruitt (1990), disclaimed the findings of Alderson and Chen. Reexamination of these two studies with additional evidence and the use of the appropriate announcement date suggests that termination of pension plans is associated with significant wealth gain to shareholders. This study also analyzes samples from periods prior to and after the imposition in 1986 of a 10 percent excise tax on recaptured excess pension assets. The empirical results suggest that shareholders experience significant positive wealth effects for the pre-tax (1980-85) period and no wealth effects for the post-tax (1986-88) period. The primary purpose of this study is to determine the impact of stock market reaction upon shareholders' wealth under the partial anticipation hypothesis. The pre-tax sample is analyzed by isolating the expected terminators using the multiple discriminant analysis model. This study finds significant positive abnormal returns only for firms that are not anticipated by the investors as potential terminators. The results of this study do not lend support to either the "separation" or the "integration" hypothesis as proposed by Alderson and Chen (1986). Instead, the results are consistent with the information hypothesis that the market reacts to unanticipated events that provide new information. Cross-sectional regression analysis of unexpected terminators suggests that the abnormal performance of stocks of pension terminating firms is explained by the firms' debt ratio and the amount of surplus pension assets. It can be inferred that firms may resort to recapturing excess pension assets as a way of financing investments internally when faced with unfavorable credit markets.

This study investigates whether the Buffett indicator can be used to make investment decisions in China. The investigation has two approaches. First, this study determines the scaling relationship between the Buffett Indicator and the GDP in China. Previous research and findings in this research regarding the scaling relationship can help international investors when comparing China with a different country as potential investment opportunities. Second, this study also examines whether the Buffett Indicator, the P/E ratio and composite models including the Buffett Indicator can be used as tools for international investors in predicting the Shanghai Index and making investment decisions for the Chinese stock market. The analysis is based on Chinese data from the World Bank, the National Bureau of Statistics of China, the Federal Reserve and the Yahoo Finance. This study finds that there is a sublinear relationship between the Buffett indicator and GDP in China and that the composite models which include the Buffett Indicator perform better to forecast the stock market in China than other indicators.

Using an early warning system (EWS) methodology, this thesis analyses the predictability of stock market crises from the perspective of behavioural fnance. Specifcally, in our EWS based on the multinomial logit model, we consider in- vestor sentiment as one of the potential crisis indicators. Identifcation of the relevant crisis indicators is based on Bayesian model averaging. The empir- ical results reveal that price-earnings ratio, short-term interest rate, current account, credit growth, as well as investor sentiment proxies are the most rele- vant indicators for anticipating stock market crises within a one-year horizon. Our thesis hence provides evidence that investor sentiment proxies should be a part of the routinely considered variables in the EWS literature. In general, the predictive power of our EWS model as evaluated by both in-sample and out-of-sample performance is promising. JEL Classifcation G01, G02, G17, G41 Keywords Stock market crises, Early warning system, In- vestor sentiment, Crisis prediction, Bayesian model averaging Title Predicting stock market crises using investor sentiment indicators

This thesis aims to investigate the long-term behaviour of the Swedish stock market under quantitative easing (QE) between the years 2015-2019 in comparison to an equally long period before the implementation of QE. The relationship is analysed within the framework of transmission channels of monetary policy and with considerations for previous research on the topic. By the means of an autoregressive distributed lag (ARDL) model, we conduct a regression analysis using the price level of the OMX Stockholm 30 (OMXS30), the value of Riksbank’s assets, the short-term interest rate and the industrial production index. The results show significant but weak evidence of a positive relationship between the OMXS30 index and the Riksbank’s assets value. Furthermore, we analyse the findings to provide an insight into the transmission of unconventional monetary policy to the stock market in a small open economy. Finally, we present some broad implications of our study, as well as suggestions for future research on the topic.

In this study, the authors examined the relationship between crude oil price and the Swedish and Norwegian stock markets. Using linear regression models the authors found that the Swedish stock market and Norwegian stock market both have a positive relation with crude oil price. This supports the hypothesis that crude oil price has a positive impact on Norwegian stock market, since Norway is an oil exporting country. However, this result contradicts a hypothesis of a negative relationship for an oil importing country like Sweden. The authors also looked into the relationship between exchange rates (Swedish krona and Norwegian krone) and oil price, which reveals that oil price is significantly negatively correlated with Swedish krona and Norwegian Krone. The study contributes with evidence from underexplored regions of the world.

In this thesis, we have built an optimal portfolio using five assets from the Japanese market. We have investigated the use of GARCH(1,1) when forecasting the volatility of our optimal portfolio. Different time periods have been considered for optimizing our results. An equally-weighted portfolio has been used as a benchmark. Our results show that the optimal portfolio we constructed is more efficient than the equally-weighted portfolio in all chosen situations.