اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدWhy Existing Machine Learning Methods Fails At Extracting the Information of Future Returns Out of Historical Sctock Prices : the Curve-Shape-Feature and Non-Curve-Shape-Feature Modes
129
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The financial time series analysis is important access to touch the complex laws of financial markets. Among many goals of the financial time series analysis, one is to construct a model that can extract the information of the future return out of the known historical stock data, such as stock price, financial news, and e.t.c. To design such a model, prior knowledge on how the future return is correlated with the historical stock prices is needed. In this work, we focus on the issue: in what mode the future return is correlated with the historical stock prices. We manually design several financial time series where the future return is correlated with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future return can be extracted from the curve shapes of the historical stock prices. By applying various kinds of existing algorithms on those pre-designed time series and real financial time series, we show that: (1) the major information of the future return is not contained in the curve-shape features of historical stock prices. That is, the future return is not mainly correlated with the historical stock prices in the CSF mode. (2) Various kinds of existing machine learning algorithms are good at extracting the curveshape features in the historical stock prices and thus are inappropriate for financial time series analysis although they are successful in the image recognition and natural language processing. That is, new models handling the NCSF series are needed in the financial time series analysis.
قيم البحث
اقرأ أيضاً
The Photon Transfer Curve (PTC) of a CCD depicts the variance of uniform images as a function of their average. It is now well established that the variance is not proportional to the average, as Poisson statistics would indicate, but rather flattens
out at high flux. This variance deficit, related to the brighter-fatter effect, feeds correlations between nearby pixels, that increase with flux, and decay with distance. We propose an analytical expression for the PTC shape, and for the dependence of correlations with intensity, and relate both to some more basic quantities related to the electrostatics of the sensor, that are commonly used to correct science images for the brighter-fatter effect. We derive electrostatic constraints from a large set of flat field images acquired with a CCD e2v 250, and eventually question the generally-admitted assumption that boundaries of CCD pixels shift by amounts proportional to the source charges. Our results show that the departure of flat field statistics from Poisson law is entirely compatible with charge redistribution during the drift in the sensor.
Some nonlinear dynamical techniques, including state-space reconstruction and correlation integral, are used to analyze the light curve of 3C 273. The result is compared with a chaotic model. The similarity between them suggests that there is a low-d
imensional chaotic attractor in the light curve of 3C 273.
The observed rotation curves of disc galaxies, ranging from late-type dwarf galaxies to early-type spirals, can be fit remarkably well simply by scaling up the contributions of the stellar and HI discs. This `baryonic scaling model can explain the fu
ll breadth of observed rotation curves with only two free parameters. For a small fraction of galaxies, in particular early-type spiral galaxies, HI scaling appears to fail in the outer parts, possibly due to observational effects or ionization of the HI. The overall success of the baryonic scaling model suggests that the well-known global coupling between the baryonic mass of a galaxy and its rotation velocity (known as the baryonic Tully-Fisher relation), applies at a more local level as well, and it seems to imply a link between the baryonic mass distribution and the distribution of total mass (including dark matter).
As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated with model
interpretability. Many machine learning algorithms induce models difficult to interpret, named black box. Moreover, people have difficulty to trust models that cannot be explained. In particular for machine learning, many groups are investigating new methods able to explain black box models. These methods usually look inside the black models to explain their inner work. By doing so, they allow the interpretation of the decision making process used by black box models. Among the recently proposed model interpretation methods, there is a group, named local estimators, which are designed to explain how the label of particular instance is predicted. For such, they induce interpretable models on the neighborhood of the instance to be explained. Local estimators have been successfully used to explain specific predictions. Although they provide some degree of model interpretability, it is still not clear what is the best way to implement and apply them. Open questions include: how to best define the neighborhood of an instance? How to control the trade-off between the accuracy of the interpretation method and its interpretability? How to make the obtained solution robust to small variations on the instance to be explained? To answer to these questions, we propose and investigate two strategies: (i) using data instance properties to provide improved explanations, and (ii) making sure that the neighborhood of an instance is properly defined by taking the geometry of the domain of the feature space into account. We evaluate these strategies in a regression task and present experimental results that show that they can improve local explanations.
We report the results of our pilot millimeter observations of periodic maser sources. Using SMA, we carried out 1.3,mm observations of G22.357$+$0.066 and G25.411$+$0.105, while ALMA 1.3 mm archival data was used in the case of G9.62+0.19E. Two conti
nuum cores (MM1 and MM2) were detected in G22.357$+$0.066, while 3 cores (MM1 -- MM3) detected in G25.411$+$0.105. Assuming dust-to-gas ratio of 100, we derived the masses of the detected cores. Using the $^{12}$CO (2-1) and $^{13}$CO (2-1) line emission, we observed gas kinematics tracing the presence of bipolar outflows in all three star-forming regions. In the cases of G22.357$+$0.066 and G9.62+0.19E, both with similar periodic maser light curve profiles, the outflowing gas is seen in the north-west south-east direction. This suggest edge-on view of the 2 sources. G25.411$+$0.105, with a contrasting light curve profile, show a spatially co-located blue and red outflow lobes, suggesting a face-on view. Our results suggest that orientation effects may play a role in determining the characteristics of the light curves of periodic methanol masers.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
