An algorithm for detecting leaks of insider information of financial markets in investment consulting.
Annotation
The paper focuses on revealing insider information leaks of financial markets during investment consulting. An original dataset was created, containing the records of the conversations between consultants and clients, presented in the formof dialogs in text format. The applicability of machine learning methods for automating the detection of leaks arising in a conversation between a consultant and a client has been studied. The authors examined the applicability of the following supervised machine learning methods for constructing and training a classifier: probabilistic (Naïve Bayes classifier), metric (k-nearest neighbors algorithm), logical (random forest), linear (support vector machine), and methods based on artificial neural networks. The paper considers various approaches to the construction of a natural language text model, such as tokenization (bag of words, word n-grams: bigrams and trigrams) and vectorization (one-hot encoding). The proposed algorithm for detecting financial markets insider information leaks is based on the use of support vector machine (SVM) and tokenization by bigrams. The obtained results demonstrate that SVM and bigram tokenization provide the highest leakage detection accuracy. The research results can be used in cybersecurity tools development, as well as for the further elaboration of natural language processing methods dealing with information security problems.
Keywords
Постоянный URL
Articles in current issue
- An approach to photogrammetric processing of indirect optical location data
- Sensing element for the formation fluid refractometer on the basis of total internal reflection
- A method for analysing the color rendering of digital cameras. Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- An analysis of methods for aberrated spot diagram center evaluation
- Investigation of the accuracy of measuring the parameters of remote objects observed by the optical-electronic system with a light field recorder
- Evaluation of permissible pixel positioning errors for displaying computer-generated holograms in projection photolithography
- The study of spontaneous domain nucleation in the interelectrode gap of phase modulator based on titanium indiffused waveguides in lithium niobate crystals
- Adaptive observer design for time-varying nonlinear systems with unknown polynomial parameters
- Development of a new plasma technology for producing pure white corundum.
- The investigation of dynamic properties of 3D-printed steel parts
- An efficient mechanism to detect and mitigate an ARP spoofing attack in software-defined networks
- Investigation of numerical approaches to modeling large-scale turbulent vortex flows in the mode of vertical take-off and landing of an aircraft.
- Mathematical modeling and identification of surface vessel model parameters
- Methodological support of the working group in predicting the results of the classification expertise
- Automatic allergy classification based on Russian unstructured medical texts
- An analysis of methods for assessing information security risks of financial institutions