Stock prices prediction via tensor decomposition and links forecast

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract: Many complex systems display fluctuations between alternative states in correspondence to tipping points. These critical shifts are usually associated with generic empirical phenomena such as strengthening correlations between entities composing the system. In finance, for instance, market crashes are the consequence of herding behaviors that make the units of the system strongly correlated, lowering their distances. Consequently, determining future distances between stocks can be a valuable starting point for predicting market down-turns. This is the scope of the work. It introduces a multi-way procedure for forecasting stock prices by decomposing a distance tensor. This multidimensional method avoids aggregation processes that could lead to the loss of crucial features of the system. The technique is applied to a basket of stocks composing the S&P500 composite index and to the index itself so as to demonstrate its ability to predict the large market shifts that arise in times of turbulence, such as the ongoing financial crisis. Terms of use: Documents inJEL Codes: C02, C63, C63.

Should You Meet the Parents? The Impact of Information on Non-Test Score Attributes on School Choice

“…We discuss here potential mechanisms driving the treatment effects unveiled in Section 5, assisted by descriptive evidence from parental surveys administered at MTP meetings. 41 Although we can ultimately offer only suggestive evidence, we argue that our results reflect the impact of providing hard-to-find information on non-test score school attributes (see Section 3).…”

“…Assuming the average competition effect is similar between exposed and unexposed parents, a one standard deviation higher exposure to treated peers increases enrolment of non-treated parents at MTP-promoted schools by 1.5 pp (= 0.55 + 0.95), almost half the direct impact of the programme 41. We report data for a survey administered in 2019.…”

Dancing with the Populist: New Parties, Electoral Rules and Italian Municipal Elections

“…This last result is consistent with FSM learning about their advantage in a runoff system as they gain political experience. 41 Balancing on observable characteristics and the MCrary test are reported in Table B. We can further apply the identification strategy developed in Section 4.2 to estimate the effect of FSM's electoral success on a set of indicators for the economic performance of the municipality.…”

Vaccination Take-Up and Health: Evidence from a Flu Vaccination Program for the Elderly

“…To investigate the role of individuals' characteristics on the vaccination decisions, we replicate our baseline analysis by splitting the sample according to the individual's health status and income. 41 Using the information on costsharing exemptions certified by the NHS, we identify four categories of individuals: (i) those affected by a chronic disease, (ii) those with poor health status and low income, (iii) those with a low income, and (iv) the remaining individuals with no certified exemptions. As mentioned in Section 2.4, since cost-sharing exemption associated with a chronic and severe health condition imply free access to a great proportion of specialist visits and drugs, we expect the cost-sharing exemption for low income to play no additional role, and thus interpret the four categories above as providing a ranking in the health-income space which improves from categories (i) to (iv).…”