scholarly journals Algo-Trading using Statistical Learning and Optimizing Sharpe Ratio and Drawdown

2021 ◽  
Vol 10 (4) ◽  
pp. 95-100
Author(s):  
Penumatcha Bharath Varma ◽  
◽  
Dr. Jaypal Medida ◽  
Neeraj Kasheety ◽  
Hanumanula Sravya ◽  
...  
Keyword(s):  
Machine Learning ◽  
Statistical Learning ◽  
20Th Century ◽  
Investment Decisions ◽  
Sharpe Ratio ◽  
Algorithmic Trading ◽  
Market Revolution ◽  
Market Conditions

Modernization in computers and Machine Learning have created new opportunities for improving the methods involved in trading, Changes have been noticed parallelly at the level of investment decisions, and at the faster executions of trades via algorithms. Nowadays 90% of the trades are placed by algorithms, to execute a transaction, algorithms that follow a trend and construct a set of instructions are used in algorithmic trading. It executes the trades more precisely by precluding the effect of human feelings on trading. It all started way back in the 20th century and nowadays it’s becoming more and more competitive, with more big players entering the market every day. Our research aims to advance the market revolution by developing an Algorithmic Trading approach that will automatically trade user strategies alongside its own algorithms for intraday trading based on different market conditions and user approach, and throughout the day invest and trade with continuous modifications to ensure the best returns for day traders and investors.

The profitability of algorithmic trading systems based on football sentiment

2020 ◽  
Vol 42 (1) ◽  
pp. 33-46
Author(s):  
Raúl Gómez-Martínez ◽  
Camila Marqués-Bogliani ◽  
Jessica Paule-Vianez
Keyword(s):  
Financial Markets ◽  
Investment Decisions ◽  
Futures Market ◽  
Algorithmic Trading ◽  
Investment Strategies ◽  
Measurable Effect ◽  
Behavioural Finance ◽  
Trading Systems ◽  
European Football

Behavioural finance has shown that investment decisions are the result of not just rational but also emotional brain processes. On the assumption that emotions affect financial markets, it would seem likely that football results might have a measurable effect on financial markets. To test this, this study describes three algorithmic trading systems based exclusively on the results of three top European football teams (Juventus, Bayern München and Paris St Germain) opening long or short positions in the next market season of the futures market of the index of each country (MIB (Milano Italia Borsa), DAX (Deutscher Aktien Index) and CAC (Cotation Assistée en Continu). Depending on the outcome of the last game played a long position was taken after a victory and a short position after a draw or defeat. The results showed that the algorithmic systems were profitable in the case of Juventus and Bayern whereas in the case of PSG, the system was profitable, but in an inverse way. This study shows that investment strategies that take account of sports sentiment could have a profitable outcome.

scholarly journals Forecasting and trading cryptocurrencies with machine learning under changing market conditions

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Helder Sebastião ◽  
Pedro Godinho
Keyword(s):  
Machine Learning ◽  
Linear Models ◽  
Test Sample ◽  
Trading Strategies ◽  
Network Activity ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Success Rates ◽  
Market Conditions ◽  
Sharpe Ratios

AbstractThis study examines the predictability of three major cryptocurrencies—bitcoin, ethereum, and litecoin—and the profitability of trading strategies devised upon machine learning techniques (e.g., linear models, random forests, and support vector machines). The models are validated in a period characterized by unprecedented turmoil and tested in a period of bear markets, allowing the assessment of whether the predictions are good even when the market direction changes between the validation and test periods. The classification and regression methods use attributes from trading and network activity for the period from August 15, 2015 to March 03, 2019, with the test sample beginning on April 13, 2018. For the test period, five out of 18 individual models have success rates of less than 50%. The trading strategies are built on model assembling. The ensemble assuming that five models produce identical signals (Ensemble 5) achieves the best performance for ethereum and litecoin, with annualized Sharpe ratios of 80.17% and 91.35% and annualized returns (after proportional round-trip trading costs of 0.5%) of 9.62% and 5.73%, respectively. These positive results support the claim that machine learning provides robust techniques for exploring the predictability of cryptocurrencies and for devising profitable trading strategies in these markets, even under adverse market conditions.

scholarly journals Evaluating the Effectiveness of the Momentum Strategy for Responsible Investment in the Russian Stock Market

2021 ◽  
Vol 93 ◽  
pp. 02020
Author(s):  
Danila Ovechkin ◽  
Liudmila Reshetnikova ◽  
Natalia Boldyreva
Keyword(s):  
Time Horizon ◽  
Investment Decisions ◽  
Sharpe Ratio ◽  
Momentum Strategy ◽  
Responsible Investment ◽  
Market Index ◽  
Monthly Return ◽  
Key Factor ◽  
Russian Stock Market ◽  
Asset Managers

In modern conditions, the integration of ESG-criteria into investment decisions of asset managers is considered as a key factor in sustainable economic development. We examine the effectiveness of the Momentum-ESG strategy based on the Responsibility and Openness Index in comparison with the Momentum strategy, which is based on the Moscow Exchange Broad Market Index, since December 2011 to December 2020. We propose an algorithm for integrating ESG criteria into momentum strategy. We select "winners" and "losers" stocks based on their monthly return. The Momentum-ESG strategy has a high Sharpe ratio for a time horizon of 12 months, the Momentum strategy - for a time horizon of 6 months. The testing of the Momentum-ESG strategy shows its greater efficiency in terms of the Sharpe ratio compared to the Momentum strategy, which does not take into account the ESG-factors, in the investing period.

scholarly journals Pengenalan Gerak Manusia Menggunakan Algoritma Relevance Vector Machine pada MSRC-12 Dataset

2020 ◽  
Vol 3 (1) ◽  
Author(s):  
Vina Ayumi ◽  
Erwin Dwika Putra
Keyword(s):  
Machine Learning ◽  
Data Processing ◽  
Statistical Learning ◽  
Gesture Recognition ◽  
Learning Theory ◽  
Relevance Vector Machine ◽  
Motion Model ◽  
Communication Tools ◽  
Machine Learning Technique ◽  
Learning Technique

Relevance vector machine is a popular machine learning technique that is motivated by statistical learning theory. RVM can be used for gesture recognition which is one of the communication tools used by humans. This study proposes an experiment using the Relevance Vector Machine (RVM) algorithm on gesture data from Microsoft Research Cambridge-12 (MSRC-12) as a proposed solution to overcome unbalanced problems in data processing. The results of the study are the accuracy for 1-person motion model reaches 100% and the lowest accuracy with 5 people the motion model reaches 96%. Graphically, the more people or models, the lower the algorithm's accuracy.

scholarly journals Review of Statistical Learning Methods in Integrated Omics Studies (An Integrated Information Science)

2018 ◽  
Vol 12 ◽  
pp. 117793221875929 ◽  
Author(s):  
Irene Sui Lan Zeng ◽  
Thomas Lumley
Keyword(s):  
Machine Learning ◽  
Statistical Learning ◽  
Information Science ◽  
Molecular System ◽  
Principal Component ◽  
Statistical Machine Learning ◽  
Learning Methods ◽  
Integrated Omics ◽  
Types Of Information ◽  
Integrated Information

Integrated omics is becoming a new channel for investigating the complex molecular system in modern biological science and sets a foundation for systematic learning for precision medicine. The statistical/machine learning methods that have emerged in the past decade for integrated omics are not only innovative but also multidisciplinary with integrated knowledge in biology, medicine, statistics, machine learning, and artificial intelligence. Here, we review the nontrivial classes of learning methods from the statistical aspects and streamline these learning methods within the statistical learning framework. The intriguing findings from the review are that the methods used are generalizable to other disciplines with complex systematic structure, and the integrated omics is part of an integrated information science which has collated and integrated different types of information for inferences and decision making. We review the statistical learning methods of exploratory and supervised learning from 42 publications. We also discuss the strengths and limitations of the extended principal component analysis, cluster analysis, network analysis, and regression methods. Statistical techniques such as penalization for sparsity induction when there are fewer observations than the number of features and using Bayesian approach when there are prior knowledge to be integrated are also included in the commentary. For the completeness of the review, a table of currently available software and packages from 23 publications for omics are summarized in the appendix.

scholarly journals Predicting Math Student Success in the Initial Phase of College With Sparse Information Using Approaches From Statistical Learning

2020 ◽  
Vol 5 ◽  
Author(s):  
Pascal Kilian ◽  
Frank Loose ◽  
Augustin Kelava
Keyword(s):  
Machine Learning ◽  
Student Success ◽  
Statistical Learning ◽  
Initial Phase ◽  
Feature Space ◽  
Risk Groups ◽  
Proof Of Concept ◽  
First Semester ◽  
Machine Learning Methods ◽  
Extensive Variable

In math teacher education, dropout research relies mostly on frameworks which carry out extensive variable collections leading to a lack of practical applicability. We investigate the completion of a first semester course as a dropout indicator and thereby provide not only good predictions, but also generate interpretable and practicable results together with easy-to-understand recommendations. As proof-of-concept, a sparse feature space together with machine learning methods is used for prediction of dropout, wherein the most predictive features have to be identified. Interpretability can be reached by introducing risk groups for the students. Implications for interventions are discussed.

scholarly journals Quantum Chemistry Meets Machine Learning

2019 ◽  
Vol 73 (12) ◽  
pp. 983-989 ◽  
Author(s):  
Alberto Fabrizio ◽  
Benjamin Meyer ◽  
Raimon Fabregat ◽  
Clemence Corminboeuf
Keyword(s):  
Machine Learning ◽  
Statistical Learning ◽  
Quantum Chemical ◽  
Large Scale ◽  
Organic Molecules ◽  
Chemical Properties ◽  
Learning Approaches ◽  
Energy Landscapes ◽  
Free Energy Landscapes ◽  
Large Scale Screening

In this account, we demonstrate how statistical learning approaches can be leveraged across a range of different quantum chemical areas to transform the scaling, nature, and complexity of the problems that we are tackling. Selected examples illustrate the power brought by kernel-based approaches in the large-scale screening of homogeneous catalysis, the prediction of fundamental quantum chemical properties and the free-energy landscapes of flexible organic molecules. While certainly non-exhaustive, these examples provide an intriguing glimpse into our own research efforts.

scholarly journals It’s a Peoples Game, Isn’t It?! A Comparison Between the Investment Returns of Business Angels and Machine Learning Algorithms

2020 ◽  
pp. 104225872094520
Author(s):  
Ivo Blohm ◽  
Torben Antretter ◽  
Charlotta Sirén ◽  
Dietmar Grichnik ◽  
Joakim Wincent
Keyword(s):  
Machine Learning ◽  
Cognitive Biases ◽  
Early Stage ◽  
Investment Decisions ◽  
Machine Learning Algorithms ◽  
Behavioral Decision Theory ◽  
Business Angels ◽  
Cognitive Limitations ◽  
Investment Returns ◽  
Angel Investment

Investors increasingly use machine learning (ML) algorithms to support their early stage investment decisions. However, it remains unclear if algorithms can make better investment decisions and if so, why. Building on behavioral decision theory, our study compares the investment returns of an algorithm with those of 255 business angels (BAs) investing via an angel investment platform. We explore the influence of human biases and experience on BAs’ returns and find that investors only outperformed the algorithm when they had extensive investment experience and managed to suppress their cognitive biases. These results offer novel insights into the role of cognitive limitations, experience, and the use of algorithms in early stage investing.

Study on Prediction of Mackey-Glass Chaotic Time Series Using Support Vector Machines

2014 ◽  
Vol 1051 ◽  
pp. 1009-1015 ◽  
Author(s):  
Ya Li Ning ◽  
Xin You Wang ◽  
Xi Ping He
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Support Vector Machines ◽  
Statistical Learning ◽  
Chaotic Time Series ◽  
Support Vector ◽  
Machine Type ◽  
Type Selection ◽  
Vector Machines ◽  
New Generation

Support Vector Machines (SVM), which is a new generation learning method based on advances in statistical learning theory, is characterized by the use of many standard technologies of machine learning such as maximal margin hyperplane, Mercel kernels and the quadratic programming. Because the best performance is obtained in many currently challenging applications, SVM has sustained wide attention, and has been become the standard tools of machine learning and data mining. But as a developing technology, SVM still have some problems and its applications are limited. In this paper, SVM and its applications in chaotic time series including predicting chaotic time series, focus on comparison in regression type selection, and kernel type selection in the same regression machine type.

Sign in / Sign up

Export Citation Format

Share Document