It is difficult to track and identify shill bidding behavior brought by the development of online auctions. In order to solve this problem, this paper used the XGBoost algorithm to build a shill bidding pre-warning model and obtained the important characteristics of identifying this behavior. By comparing with other mainstream algorithms, it is found that the XGBoost algorithm has the highest accuracy in predicting the risk of shill bidding behavior, reaching 99.6%. Through the experiment and comparison of the number of features, three key indicators for identifying shill bidding behavior are found, which provides an accurate range for the attack and prevention. The research in this paper improves the identification ability of shill bidding behavior and reduces the scope of the identification characteristics of shill bidding behavior, which will effectively curb the continuous spread of shill bidding behavior.
KEYWORDS: Cultural heritage, Reselling, Mathematical modeling, Data modeling, Time series analysis, Information security, Computer security, Safety, Quantitative analysis, Statistical methods
Cultural Heritage is a witness to human history, and its preservation has become a worldwide consensus. However, heritage crime is still rampant, and the protection of cultural heritages still needs excellent efforts. This paper analyzes the crime pattern of cultural heritage from the time series perspective and proposes a targeted early warning framework. The trends of the four heritage crime types were summarized on weekly, monthly, annual and decadal time scales. The upstream and downstream heritage crimes were strongly correlated on the daily time scale, with 90% of years correlated on the scale of 0.01. For different provinces and different types of cultural heritage crimes, a comprehensive early warning model framework is established using a combination of Prophet model prediction and qualitative analysis, and the optimal prediction horizon is given. The analysis results of this paper provide a viable path for applying heritage data to conservation work. It helps to prevent and control heritage crimes and provides ideas for the information construction of heritage security.
The barefoot footprint is a common trace material evidence in the crime scene, and it is an important basis for investigating and solving the case. However, the identification of barefoot footprint is mostly realized by manual operation, which is easily affected by subjective factors. It is difficult to compare and identify a large number of barefoot footprint samples. This paper puts forward a variety of barefoot similarity measurement methods, and uses MATLAB software to realize the automatic segmentation, extraction and comparison of the physical and morphological features of barefoot footprints. After image binarization, open operation and closed operation by corrosion and expansion processing, convex hull operation, edge detection and so on, by using many kinds of similarity measurement methods, the features of the footprint can be extracted completely and calculated accurately. According to the measurement principle of different "distance" in computer vision image processing and machine learning, an algorithm is designed to measure the similarity of 120 barefoot footprint samples imprinted by the same person and different people. The accuracy of the algorithm is tested by comparing the calculation results, so that the algorithm can be applied in practice.
In recent years, driven by the huge profits in the illegal cultural relics circulation market, smuggling and excavation of cultural relics have been repeated, and the situation of heritage crimes has become more and more serious. It is important to understand the occurrence pattern of excavation-type heritage crimes and construct a time-series prediction model of excavation-type heritage crimes to prevent them. This paper uses the random forests algorithm to construct a time-series prediction model of heritage crimes, which effectively solves the problem of poor timeliness of traditional prevention methods and is an attempt in the field of heritage crimes prediction. This paper constructs a time-series data of heritage crimes at several time scales and finds that the model has the best prediction effect when the time step is set to 30. It suggests that there may be a certain pattern of occurrence of excavation-type heritage crimes at the monthly scale. The findings of this paper are expected to provide decision support for the deployment of prevention and control resources for protected heritage units.
Analyzing the research changes of interrogation methods in our country and revealing the hot topics and research trends in this field is of great significance for improving interrogation strategies and realizing the transformation of interrogation methods. This thesis uses the papers on the subject of "interrogation method" in CNKI database from 2002 to 2021 as the data source and uses CiteSpace software for visual analysis. The results show that the hot topics in the research field of interrogation methods include investigator, evidence, human rights protection, interrogation skill, etc. While the research trends mainly focus on major case, repeated confession, confession psychology and so forth. As the current related research is still weak in terms of academic cooperation, research methods, and foreign reference, it is recommended to increase academic exchanges and cooperation in the future, strengthen interdisciplinary research, and learn from international advanced experience based on our country's national conditions, so as to expand the breadth and depth of research on interrogation methods.
Currently, for the problem of personal credit risk identification, the most commonly used method is to optimize the parameters of the model through bionic algorithms to obtain higher accuracy, but it may face the risk of lower precision. Some scholars also discussed the identification of personal credit risk from the perspective of combination models. From the perspective of integrated learning, based on C5.0 algorithm and using boosting technology, this paper constructs the boosting-c5.0 personal credit risk identification model, and uses UCI German personal credit data set to verify the performance of the model. The study found that the accuracy, recall, precision and AUC value of boosting-C5.0 model are better than SVM, logistic and C5.0 models.
KEYWORDS: Data modeling, Performance modeling, Machine learning, Data processing, Statistical modeling, Neural networks, Binary data, Process modeling, Detection and tracking algorithms, Algorithm development
In recent years, the auction industry has developed rapidly, and online auctions have become increasingly popular. However, the development of online auctions has also brought risks such as Shill bidding. This paper builds a Shill bidding prediction model based on support vector machine algorithm to solve the problem of difficulty in predicting Shill bidding behavior. Through the sorting and analysis of the characteristic data in the Shill bidding cases, ten indicators that are significantly related to the Shill bidding behavior have been obtained. In order to overcome the imbalance problem of the training set, a sampling balance mechanism is introduced to sample the data set. By comparing the calculation results of logistic regression and naïve Bayes algorithm, it is found that the support vector machine algorithm has the highest accuracy of Shill bidding risk prediction, reaching more than 99.2%. This study could not only improve the auction industry's ability to monitor, analyse, and judge the early warning, monitoring, analysis and judgment of bidding behavior. It could also guarantee the healthy and sound development of bidding work, and play a role in escorting social and economic development.
In the context of the era of big data, the emergence of e-commerce platforms has brought many opportunities and risks. Due to the COVID-19, e-commerce has achieved unprecedented development, and e-commerce fraud has severely damaged the healthy economic environment. This paper uses the RUSBoost algorithm to build an e-commerce fraud risk prediction model, and verifies the predictive performance of the model through data experiments. The results show that it has a high accuracy rate for identifying e-commerce fraud. If the model is applied to e-commerce, the losses caused by ecommerce fraud could be avoided in time. At present, there are fewer e-commerce fraud risk prediction models and have a wide development prospection.
In recent years, with the continuous expansion of the business scope of auto insurance, the crime of auto insurance fraud
is becoming frequent. The establishment of auto insurance fraud detection model has become an important measure to
ensure the stable development of auto insurance industry. This paper builds an auto insurance fraud detection model based
on Logistic-SVM, which could solve the problem that the original model needs lots of variables. Firstly, the importance
of characteristic variables is sorted by SVM model, and ten characteristic variables are selected according to the objective
reality. By comparing with the traditional single logistic regression and SVM algorithm, it is found that the Logistic-SVM algorithm has a better detection effect on auto insurance fraud. The accuracy of Logistic-SVM is 96.1%, which is
2% higher than that of logistic-regression and 0.7% higher than that of SVM. The research of this paper could not only
improve the practicability of machine learning model in the field of auto insurance fraud detection, but also escort the
prosperity and development of auto insurance industry.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.