Do you want to publish a course? Click here

Developing an Optimal Financial Trading System Using Artificial Intelligent Techniques

تطوير نظام أمثليّ للتداول المالي باستخدام تقنيات الذكاء الصُنعي

1942   0   24   0 ( 0 )
 Publication date 2018
and research's language is العربية
 Created by Shamra Editor




Ask ChatGPT about the research

In this paper, it has merged two techniques of the artificial intelligent, they are the ants colony optimization algorithm and the genetic algorithm, to The recurrent reinforcement learning trading system optimization. The proposed trading system is based on an ant colony optimization algorithm and the genetic algorithm to select an optimal group of technical indicators, and fundamental indicators.


Artificial intelligence review:
Research summary
تتناول هذه الدراسة تطوير نظام تداول مالي باستخدام تقنيات الذكاء الاصطناعي، حيث تم دمج خوارزمية أمثلية مستعمرة النمل (ACO) والخوارزمية الجينية (GA) مع نظام التعلّم المُعزّز العودي (RRL) لتحسين أداء التداول. تم اختبار النظام المقترح باستخدام بيانات سوق دمشق للأوراق المالية، وأظهرت النتائج تحسنًا في أداء التداول من خلال زيادة عدد الشركات ذات نسبة Sharpe الموجبة وتحقيق قيم أفضل لنسبتي Treynor و Jensen. يعتمد النظام على اختيار مجموعة مثالية من المؤشرات الفنية والأساسية لتحسين أداء التداول، مما يعزز الربحية والاستقرار مقارنة بأنظمة التداول السابقة RRL و GA-RRL.
Critical review
دراسة نقدية: تعتبر هذه الدراسة خطوة مهمة نحو تحسين أنظمة التداول المالي باستخدام تقنيات الذكاء الاصطناعي، إلا أن هناك بعض النقاط التي يمكن النظر فيها لتحسين البحث. أولاً، قد يكون من المفيد توسيع نطاق البيانات المستخدمة لتشمل أسواق مالية أخرى لضمان تعميم النتائج. ثانيًا، يمكن النظر في دمج تقنيات ذكاء اصطناعي أخرى مثل خوارزمية النحل أو أسراب الطيور لتحسين اختيار المؤشرات. أخيرًا، يمكن تحسين الدراسة من خلال تحليل تأثير العوامل الاقتصادية والسياسية على أداء النظام المقترح، مما يضيف بعدًا إضافيًا لفهم أداء النظام في ظروف مختلفة.
Questions related to the research
  1. ما هي التقنيات المستخدمة في تطوير نظام التداول المقترح؟

    تم استخدام خوارزمية أمثلية مستعمرة النمل (ACO) والخوارزمية الجينية (GA) مع نظام التعلّم المُعزّز العودي (RRL) لتطوير نظام التداول المقترح.

  2. ما هي البيانات التي تم استخدامها لاختبار النظام المقترح؟

    تم استخدام البيانات اليومية لسوق دمشق للأوراق المالية لاختبار النظام المقترح.

  3. ما هي المؤشرات المستخدمة لتحسين أداء التداول في النظام المقترح؟

    تم استخدام مجموعة من المؤشرات الفنية والأساسية التي تم اختيارها باستخدام خوارزميات ACO و GA لتحسين أداء التداول.

  4. ما هي النتائج الرئيسية التي توصلت إليها الدراسة؟

    أظهرت النتائج تحسنًا في أداء التداول من خلال زيادة عدد الشركات ذات نسبة Sharpe الموجبة وتحقيق قيم أفضل لنسبتي Treynor و Jensen، مما يعزز الربحية والاستقرار مقارنة بأنظمة التداول السابقة.


References used
J. Moody and M. Saffell, “Reinforcement Learning for Trading Systems and Portfolios,” Kdd, pp. 279–283, 1998
G. Molina, “Stock Trading with Recurrent Reinforcement Learning ( RRL ),” Direct
J. Cumming and L. Dickens, “An Investigation into the Use of Reinforcement Learning Techniques within the Algorithmic Trading Domain,” 2015
rate research

Read More

The Research Aims: Syrian organizations keep large amounts of information and data about their personnel in their IT systems. This information, however, is often left unutilized or may be analyzed through statistical methods. In this study, DM is considered a solution for analyzing HR data and explore knowledge from data stored in some Syrian organization through two major stages: Stage A: Using results of Semi-Annual performance evaluation process to build prototype showed in (Fig. 6) to accomplish two tasks: 1. Building a models to predict appropriate job function for an employee through majority principle and using high accuracy result to increase the number of training data and make it self-learning model. 2. Choose most important attributes that used in classify methods to use it in personnel selection and recruitment. Stage B: Using data of Time & Attendance to analysis personnel activity through clustering methods and building many meaningful groups.
This research tackles autolanding a power-off fixed-wing Unmanned Aerial Vehicle (UAV) on a level or uphill landing strip with limited dimensions. New approaches to path planning, guidance, and control are proposed for the final approach and landin g stages. These approaches address mid-sized UAVs assuming that the aircraft has only standard control surfaces, i.e. the elevator, the rudder, and the ailerons. This problem has not been covered by the existing flight control literature.
In this research we introduce a regularization based feature selection algorithm to benefit from sparsity and feature grouping properties and incorporate it into the medical image classification task. Using this group sparsity (GS) method, the wh ole group of features are either selected or removed. The basic idea in GS is to delete features that do not affect the retrieval process, instead of keeping them and giving these features small weights. Therefore, GS improves system by increasing accuracy of the results, plus reducing space and time requirements needed by the system.
The word "massive data" spread in 2017 and became the most common in the industry of advanced technology, it uses automated learning that allows computers to analyze past data and predict future data widely in familiar places. Non-automated learning professionals can use it too. To study the analytical method of statistical Automatic learning, it is necessary to identify the concept of artificial intelligence and its main classification and analytical techniques included and represent in automatic learning and deep learning. Automatic learning has developed thanks to some breakthroughs in artificial intelligence. It is an awareness of the efficient teaching of computers in addition to the invention of the Internet. Neural networks have an important role to play in teaching computers, such as humans, where they use data they can access to make decisions. There are many algorithms for learning about automatic learning. In our study, we demonstrate the methods and applications of automated statistical analysis, such as regression analysis, decision tree, middle method k and association analysis.
This paper presents a method for finding online adaptive optimal controllers for continuous-time linear systems without knowing the system dynamical matrices. The proposed method employs one of Intelligent Operations Research Techniques, this tech nique is the adaptive dynamic programming, to iteratively solve the algebraic Riccati equation using the online information of state and input, without requiring the a priori knowledge of the system dynamics. In addition, all iterations can be conducted by using repeatedly the same state and input information on some fixed time intervals. A practical online algorithm is developed in this paper, and is applied to the controller design for a turbocharged diesel engine with exhaust gas recirculation.
comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا