CN110189034A - A kind of insider trading method of identification based on model-naive Bayesian - Google Patents
A kind of insider trading method of identification based on model-naive Bayesian Download PDFInfo
- Publication number
- CN110189034A CN110189034A CN201910470710.3A CN201910470710A CN110189034A CN 110189034 A CN110189034 A CN 110189034A CN 201910470710 A CN201910470710 A CN 201910470710A CN 110189034 A CN110189034 A CN 110189034A
- Authority
- CN
- China
- Prior art keywords
- insider trading
- insider
- trading
- test target
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of insider trading method of identification based on model-naive Bayesian obtains the insider trading sample data set under the different event time window phase;It constructs and trains the Bayesian recognition model about insider trading;It obtains test target and collects the feature of test target;Identify the result that insider trading whether occurs obtained to test target using Bayesian recognition model.Method of the invention is quickly identified to whether stock sample occurs insider trading, provides a kind of efficient and practical means for insider trading supervision;With being continuously increased for sample, Bayesian recognition model of the invention has higher insider trading accuracy of identification.
Description
Technical field
The invention belongs to Securities Market Regulation fields, and in particular to a kind of insider trading knowledge based on model-naive Bayesian
Other method.
Background technique
The securities market insider trading behavior severe jamming normal operation of stock market especially compromises medium and small investors benefit
Benefit.In recent years, how to identify that insider trading has become the hot spot of academia's concern.
Naive Bayes Classifier is one of learning efficiency, the preferable classifier of classifying quality compared with other classifiers,
Its advantage is simple for algorithm logic, be easily achieved, algorithm performance is stablized etc..The basis of Naive Bayes Classification is probability inference,
The probability that each condition known occurs, completes reasoning and decision task.
Therefore, a kind of insider trading method of identification based on model-naive Bayesian is studied.
Summary of the invention
The technical problem of the invention normal operation of stock market that has been the insider trading behavior severe jamming of securities market, damage
Investors' interest, is not easy to be identified, and the object of the present invention is to provide a kind of, and the insider trading based on model-naive Bayesian is known
Other method is quickly identified to whether security share of market occurs insider trading.
The technical scheme is that a kind of insider trading method of identification based on model-naive Bayesian, including following step
Suddenly,
Step 1: obtaining the insider trading sample data set under the different event time window phase;
Step 2: constructing and train the Bayesian recognition model about insider trading;
Step 3: obtaining test target and collect the feature of test target;
Step 4: identifying the knot that insider trading whether occurs obtained to test target using Bayesian recognition model
Fruit;
Step 5: judging whether there is next test target;
Step 5.1: if there is next test target, thening follow the steps 3;
Step 5.2: if terminating without next test target.
Further, in step 2, the Bayesian recognition model of the building and training about insider trading, including it is following
Step,
Step 2.1: selection feature;
Step 2.2: selection training sample;
Step 2.3: probability P (C is calculated separately to inside story transaction categories and non-insider trading classificationi), CiFor sample classification,
C1Indicate insider trading, C2Indicate non-insider trading;
Step 2.4: calculating each characteristic attribute the conditional probability P (C of all categories dividedi|x);
Step 2.5: calculating separately and show that each sample belongs to insider trading classification or the posteriority of non-insider trading classification is general
Rate value
Step 2.6: setting insider trading threshold value η1With non-insider trading threshold value η2, judge whether test sample occurs inside story
Transaction;
Step 2.6.1: ifThen judge that insider trading occurs;
Step 2.6.2: ifThen judge that insider trading does not occur;
Step 2.6.3: ifAndIt does not make a decision then.
Further, in step 1, insider trading sample data set further includes listed company's wealth disclosed in securities market personal share
Business index, company governance index and personal share securities market Microscopic Indexes.
The beneficial effects of the invention are as follows building Bayesian recognition models to give fastly whether stock sample occurs insider trading
Speed identification provides a kind of efficient and practical means for insider trading supervision;It is of the invention with being continuously increased for sample
Bayesian recognition model has higher insider trading accuracy of identification.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is the flow chart of the insider trading method of identification based on model-naive Bayesian.
Fig. 2 is Naive Bayes Classification process schematic.
Specific embodiment
As shown in Figure 1, the insider trading method of identification based on model-naive Bayesian, includes the following steps,
Step 1: obtaining the insider trading sample data set under the different event time window phase;
Step 2: constructing and train the Bayesian recognition model about insider trading;
Step 3: obtaining test target and collect the feature of test target;
Step 4: identifying the knot that insider trading whether occurs obtained to test target using Bayesian recognition model
Fruit;
Step 5: judging whether there is next test target;
Step 5.1: if there is next test target, thening follow the steps 3;
Step 5.2: if terminating without next test target.
In step 2, the Bayesian recognition model of the building and training about insider trading includes the following steps,
Step 2.1: selection feature;
Step 2.2: selection training sample;
Step 2.3: probability P (C is calculated separately to inside story transaction categories and non-insider trading classificationi), CiFor sample classification,
C1Indicate insider trading, C2Indicate non-insider trading;
Step 2.4: calculating each characteristic attribute the conditional probability P (C of all categories dividedi|x);
Step 2.5: calculating separately and show that each sample belongs to insider trading classification or the posteriority of non-insider trading classification is general
Rate value
Step 2.6: setting insider trading threshold value η1With non-insider trading threshold value η2, judge whether test sample occurs inside story
Transaction;
Step 2.6.1: ifThen judge that insider trading occurs;
Step 2.6.2: ifThen judge that insider trading does not occur;
Step 2.6.3: ifAndIt does not make a decision then.
In step 1, insider trading sample data set further includes Company Financial index, public affairs disclosed in securities market personal share
Department administers index and personal share securities market Microscopic Indexes.
As shown in Fig. 2, detailed process is as follows for naive Bayesian insider trading identification:
A data sample X is given, with n dimensional feature vector X={ x1,x2,…,xnIndicate, sample X is described respectively at n
Feature { A1,A2,…,AnOn characteristic value;According to Bayes' theorem
P (X) refers to that any one data object meets the probability of sample X in formula.CiFor sample classification, wherein C1In indicating
Curtain transaction, C2Indicate non-insider trading.P(Ci) it is that any one data sample belongs to class CiProbability, according to P (Ci)=si/ s meter
It calculates, siIt is class CiMiddle number of training, s are training sample sums.
When label whether given sample insider trading, it is assumed that each characteristic value condition of reciprocity is independent, P (X/Ci) pass through under
Formula calculates:
P(X|Ci)P(Ci)=P (x1|Ci)P(x2|Ci)…P(xn|Ci)
I.e.
Probability P (xk/Ci) estimated by training sample, in the present invention, feature AkIt is continuous, it is assumed that characteristic value is obeyed high
This distribution,
In formulaIt is characterized AkGauss specification density function,WithFor training sample
Middle classification is CiFeature AkMean value and variance.
For test target sample E, to each class CiIt calculatesSet insider trading threshold value η1With it is non-
Insider trading threshold value η2, whenWhen then the test sample belong to insider trading, whenWhen, then the test sample belongs to non-insider trading, when not up to either threshold, does not make a decision.
In embodiment, respectively in terms of subsidiary company equity structure, financial data, improvement system and securities market Microscopic
18 characteristic indexs are chosen and calculate, as shown in Table 1.
One characteristic index table of table
By taking China Securities Regulatory Commission announces the 171 insider trading cases occurred as an example, corresponding same industry, same year are collected
Insider trading stock sample does not occur for part as control, and building contains the insider trading sample data set of 335 data samples, to shellfish
This identification model of leaf is trained.
Specific manifestation of the Bayesian recognition model in example is as shown in Table 2, generates time point with inside news and is pushed forward 90
The day of trade is data collection time window.Since insider trading case harmfulness is larger, biggish judgment threshold is generally taken,
In this embodiment, for insider trading threshold value η1With non-insider trading threshold value η20.80 is taken to be used as judgment threshold respectively.
The insider trading recognition result of two Bayesian recognition model of table
In practical applications, relevant department can choose different insider trading sensitive periods as recognition time according to different situations
The length of window is identified to whether personal share occurs insider trading behavior.
Claims (3)
1. a kind of insider trading method of identification based on model-naive Bayesian, which is characterized in that include the following steps,
Step 1: obtaining the insider trading sample data set under the different event time window phase;
Step 2: constructing and train the Bayesian recognition model about insider trading;
Step 3: obtaining test target and collect the feature of test target;
Step 4: identifying the result that insider trading whether occurs obtained to test target using Bayesian recognition model;
Step 5: judging whether there is next test target;
Step 5.1: if there is next test target, thening follow the steps 3;
Step 5.2: if terminating without next test target.
2. the insider trading method of identification according to claim 1 based on model-naive Bayesian, which is characterized in that step 2
In, the Bayesian recognition model of the building and training about insider trading includes the following steps,
Step 2.1: selection feature;
Step 2.2: selection training sample;
Step 2.3: probability P (C is calculated separately to inside story transaction categories and non-insider trading classificationi), CiFor sample classification, C1Table
It is shown with insider trading, C2Indicate non-insider trading;
Step 2.4: calculating each characteristic attribute the conditional probability P (C of all categories dividedi|x);
Step 2.5: calculating separately the posterior probability values for showing that each sample belongs to insider trading classification or non-insider trading classification
Step 2.6: setting insider trading threshold value η1With non-insider trading threshold value η2, judge whether test sample occurs insider trading;
Step 2.6.1: ifThen judge that insider trading occurs;
Step 2.6.2: ifThen judge that insider trading does not occur;
Step 2.6.3: ifAndIt does not make a decision then.
3. the insider trading method of identification according to claim 1 or 2 based on model-naive Bayesian, which is characterized in that step
In rapid 1, insider trading sample data set further includes Company Financial index, company governance index disclosed in securities market personal share
And personal share securities market Microscopic Indexes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470710.3A CN110189034A (en) | 2019-05-31 | 2019-05-31 | A kind of insider trading method of identification based on model-naive Bayesian |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910470710.3A CN110189034A (en) | 2019-05-31 | 2019-05-31 | A kind of insider trading method of identification based on model-naive Bayesian |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110189034A true CN110189034A (en) | 2019-08-30 |
Family
ID=67719444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910470710.3A Pending CN110189034A (en) | 2019-05-31 | 2019-05-31 | A kind of insider trading method of identification based on model-naive Bayesian |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110189034A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111199419A (en) * | 2019-12-19 | 2020-05-26 | 成都数联铭品科技有限公司 | Method and system for identifying abnormal stock transaction |
CN111768205A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Attack transaction identification method and system |
-
2019
- 2019-05-31 CN CN201910470710.3A patent/CN110189034A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111199419A (en) * | 2019-12-19 | 2020-05-26 | 成都数联铭品科技有限公司 | Method and system for identifying abnormal stock transaction |
CN111199419B (en) * | 2019-12-19 | 2023-09-15 | 成都数联铭品科技有限公司 | Stock abnormal transaction identification method and system |
CN111768205A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Attack transaction identification method and system |
CN111768205B (en) * | 2020-06-24 | 2023-08-18 | 中国工商银行股份有限公司 | Attack transaction identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9286693B2 (en) | Method and apparatus for detecting abnormal movement | |
Muthukannan et al. | Classification of diseased plant leaves using neural network algorithms | |
Hui et al. | An application of support vector machine to companies’ financial distress prediction | |
WO2021088499A1 (en) | False invoice issuing identification method and system based on dynamic network representation | |
Wang et al. | Market index and stock price direction prediction using machine learning techniques: an empirical study on the KOSPI and HSI | |
CN102956023A (en) | Bayes classification-based method for fusing traditional meteorological data with perception data | |
Momeni et al. | Clustering stock market companies via k-means algorithm | |
Lao et al. | Gaussian mixture model-based speed estimation and vehicle classification using single-loop measurements | |
CN104156945A (en) | Method for segmenting gray scale image based on multi-objective particle swarm optimization algorithm | |
CN106023159B (en) | Facilities vegetable leaf portion scab image partition method and system | |
CN110046672A (en) | A kind of determining method of bank electronic channel exception transaction based on semi-supervised learning | |
CN103617259A (en) | Matrix decomposition recommendation method based on Bayesian probability with social relations and project content | |
CN110189034A (en) | A kind of insider trading method of identification based on model-naive Bayesian | |
Syarif et al. | Data mining approaches for network intrusion detection: from dimensionality reduction to misuse and anomaly detection | |
CN111160959A (en) | User click conversion estimation method and device | |
CN110458022A (en) | It is a kind of based on domain adapt to can autonomous learning object detection method | |
CN104573701B (en) | A kind of automatic testing method of Tassel of Corn | |
Hui et al. | Inter-class angular loss for convolutional neural networks | |
CN111724241B (en) | Enterprise invoice virtual issuing detection method based on dynamic edge feature graph annotation meaning network | |
Consoli et al. | Neural forecasting of the Italian sovereign bond market with economic news | |
Hájek et al. | Municipal revenue prediction by ensembles of neural networks and support vector machines | |
CN111625578B (en) | Feature extraction method suitable for time series data in cultural science and technology fusion field | |
CN103366163B (en) | Face detection system and method based on incremental learning | |
Yazdani et al. | Fuzzy classification method in credit risk | |
CN106874944A (en) | A kind of measure of the classification results confidence level based on Bagging and outlier |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190830 |
|
RJ01 | Rejection of invention patent application after publication |