scholarly journals Modeling Investor Behavior Using Machine Learning: Mean-Reversion and Momentum Trading Strategies

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-14
Author(s):  
Thiago Christiano Silva ◽  
Benjamin Miranda Tabak ◽  
Idamar Magalhães Ferreira
Keyword(s):  
Machine Learning ◽  
Ad Hoc ◽  
Methodological Approach ◽  
Investment Decisions ◽  
Daily Basis ◽  
Investor Behavior ◽  
Machine Learning Techniques ◽  
Investment Strategies ◽  
Academic Degree ◽  
Momentum Trading

We model investor behavior by training machine learning techniques with financial data comprising more than 13,000 investors of a large bank in Brazil over 2016 to 2018. We take high-frequency data on every sell or buy operation of these investors on a daily basis, allowing us to fully track these investment decisions over time. We then analyze whether these investment changes correlate with the IBOVESPA index. We find that investors decide their investment strategies using recent past price changes. There is some degree of heterogeneity in investment decisions. Overall, we find evidence of mean-reverting investment strategies. We also find evidence that female investors and higher academic degree have a less pronounced mean-reverting strategy behavior comparatively to male investors and those with lower academic degree. Finally, this paper provides a general methodological approach to mitigate potential biases arising from ad-hoc design decisions of discarding or introducing variables in empirical econometrics. For that, we use feature selection techniques from machine learning to identify relevant variables in an objective and concise way.

PATTERNS OF PREPOSITIONAL ATTACHMENTS — WHERE DICTIONARY SEMANTICS MEETS CORPUS STATISTICS

2000 ◽  
Vol 14 (06) ◽  
pp. 809-838 ◽  
Author(s):  
SANDA M. HARABAGIU
Keyword(s):  
Machine Learning ◽  
Information Extraction ◽  
Learning Process ◽  
Wall Street Journal ◽  
Ad Hoc ◽  
Machine Learning Techniques ◽  
Journal Articles ◽  
Wall Street ◽  
Web Documents ◽  
Learning Techniques

This paper presents a novel methodology of disambiguating prepositional phrase attachments. We create patterns of attachments by classifying a collection of prepositional relations derived from Treebank parses. As a by-product, the arguments of every prepositional relation are semantically disambiguated. Attachment decisions are generated as the result of a learning process, that builds upon some of the most popular current statistical and machine learning techniques. We have tested this methodology on (1) Wall Street Journal articles, (2) textual definitions of concepts from a dictionary and (3) an ad hoc corpus of Web documents, used for conceptual indexing and information extraction.

Algorithmic Machine Learning for Prediction of Stock Prices

2019 ◽  
pp. 142-169
Author(s):  
Mirza O. Beg ◽  
Mubashar Nazar Awan ◽  
Syed Shahzaib Ali
Keyword(s):  
Machine Learning ◽  
Stock Prices ◽  
Prediction Models ◽  
Stock Exchange ◽  
Moving Average ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Daily News ◽  
Trading Decisions

Stock markets and relevant entities generate enormous amounts of data on a daily basis and are accessible from various channels such as stock exchange, economic reviews, and employer monetary reports. In recent times, machine learning techniques have proven to be very helpful in making better trading decisions. Machine learning algorithms use complex logic to observe and learn the behavior of stocks using historical data which can be used to predict future movements of the stock. Technical indicators such as rolling mean, momentum, and exponential moving average are calculated to convert the data into meaningful information. Furthermore, this information can be used to build machine learning prediction models that learn different patterns in the data and make future predictions for accurate financial forecasting. Additional factors that are being used for stock prediction include social media influences and daily news on trading stocks. Considering these qualitative and quantitative features at the same time result in improved prediction models.

Anomaly-Based Intrusion Detection Systems for Mobile Ad Hoc Networks

2021 ◽  
Vol 12 (2) ◽  
pp. 11-32
Author(s):  
Sharada Ramakrishna Valiveti ◽  
Anush Manglani ◽  
Tadrush Desai
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Ad Hoc Networks ◽  
Ad Hoc ◽  
Detection System ◽  
Machine Learning Techniques ◽  
Heterogeneous Environments ◽  
Topology Management ◽  
Data Set ◽  
Hoc Networks

Ad hoc networks are used in heterogeneous environments like tactical military applications, where no centrally coordinated infrastructure is available. The network is required to perform self-configuration, dynamic topology management, and ensure the self-sustainability of the network. Security is hence of paramount importance. Anomaly-based intrusion detection system (IDS) is a distributed activity carried out by all nodes of the network in a cooperative manner along with other related network activities like routing, etc. Machine learning and its advances have found a promising place in anomaly detection. This paper describes the journey of defining the most suitable routing protocol for implementing IDS for tactical applications, along with the selection of the related suitable data set. The paper also reviews the latest machine learning techniques, implementation capabilities, and limitations.

scholarly journals Early Detection of Cardiovascular Disease using Machine learning Techniques an Experimental Study

2020 ◽  
Vol 9 (3) ◽  
pp. 635-641
Keyword(s):  
Machine Learning ◽  
Proper Time ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
The Other ◽  
Machine Learning Techniques ◽  
Entire Body ◽  
Time Data ◽  
Learning Techniques ◽  
Health Related

Human body prioritizes the heart as the second most important organ after the brain. Any disruption in the heart ultimately leads to disruption of the entire body. Being the members of modern era, enormous changes are happening to us on a daily basis that impact our lives in one way or the other. A major disease among top five fatal diseases includes the heart disease which has been consuming lives worldwide. Therefore, the prediction of this disease is of prime importance as it will enable one to take a proper and needful approach at a proper time. Data mining and machine learning are taking out and refining of useful information from a massive amount of data. It is a basic and primary process in defining and discovering useful information and hidden patterns from databases. The flexibility and adaptability of optimization algorithms find its use in dealing with complex non -linear problems. Machine Learning techniques find its use in medical sciences in solving real health-related issues by early prediction and treatment of various diseases. In this paper, six machine learning algorithms are used and then compared accordingly based on the evaluation of performance. Among all classifiers, decision tree outperforms over the other algorithms with a testing accuracy of 97.29%.

Bridge Response and Heavy Truck Classification Framework Based on a Two-Step Machine Learning Algorithm

2021 ◽  
pp. 036119812110520
Author(s):  
Fiorella Mete ◽  
David J. Corr ◽  
Michael P. Wilbur ◽  
Ying Chen
Keyword(s):  
Machine Learning ◽  
Ad Hoc ◽  
Learning Algorithm ◽  
Classification Tree ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Classification Framework ◽  
Learning Techniques ◽  
Tree Methods ◽  
Step Algorithm

Collecting information on heavy trucks and monitoring the bridges which they regularly cross is important for many facets of infrastructure management. In this paper, a two-step algorithm is developed using bridge and truck data, by deploying sequentially unsupervised and supervised machine learning techniques. Longitudinal clustering of bridge data, concerning strain waveforms, is adopted to perform the first step of the algorithm, while image visual inspection and classification tree methods are applied to truck data concurrently in the second step. Both bridge and truck traffic must be monitored for a limited, yet significant, amount of time to calibrate the algorithm, which is then used to build a classification framework. The framework provides the same benefits of two data collection systems while only one needs to be operative. Depending on which monitoring system remains available, the framework enables the use of bridge data to identify the truck’s profile which generated it, or to estimate bridge response given the truck’s information. As a result, the present study aims to provide decision-makers with an effective way to monitor the whole bridge-traffic system, bridge managers to plan effective maintenance, and policymakers to develop ad hoc regulations.

scholarly journals Interpolation of Instantaneous Air Temperature Using Geographical and MODIS Derived Variables with Machine Learning Techniques

2019 ◽  
Vol 8 (9) ◽  
pp. 382 ◽  
Author(s):  
Marcos Ruiz-Álvarez ◽  
Francisco Alonso-Sarria ◽  
Francisco Gomariz-Castillo
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Air Temperature ◽  
Cross Validation ◽  
Daily Basis ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector

Several methods have been tried to estimate air temperature using satellite imagery. In this paper, the results of two machine learning algorithms, Support Vector Machines and Random Forest, are compared with Multiple Linear Regression and Ordinary kriging. Several geographic, remote sensing and time variables are used as predictors. The validation is carried out using two different approaches, a leave-one-out cross validation in the spatial domain and a spatio-temporal k-block cross-validation, and four different statistics on a daily basis, allowing the use of ANOVA to compare the results. The main conclusion is that Random Forest produces the best results (R 2 = 0.888 ± 0.026, Root mean square error = 3.01 ± 0.325 using k-block cross-validation). Regression methods (Support Vector Machine, Random Forest and Multiple Linear Regression) are calibrated with MODIS data and several predictors easily calculated from a Digital Elevation Model. The most important variables in the Random Forest model were satellite temperature, potential irradiation and cdayt, a cosine transformation of the julian day.

Sign in / Sign up

Export Citation Format

Share Document