scispace - formally typeset
Search or ask a question
Topic

Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.


Papers
More filters
Patent
01 Apr 2021
TL;DR: In this paper, a method for constructing a cloud network alarm root cause relational tree model, a device, and a storage medium is presented, which includes mining, according to a frequent itemset, first alarm data of a traditional network, and performing, by using a traditional expert knowledge database as a label, feature extraction on the first alarm tree model to obtain a first feature parameter.
Abstract: A method for constructing a cloud network alarm root cause relational tree model, a device, and a storage medium. The method comprises: mining, according to a frequent itemset, first alarm data of a traditional network to obtain a first alarm tree model, and performing, by using a traditional expert knowledge database as a label, feature extraction on the first alarm tree model to obtain a first feature parameter; customizing, according to a pre-determined classification rule, classification types, and determining, by means of machine learning, a classification weight value corresponding to each of the classification types in the first alarm tree model; and mining, according to the frequent itemset, second alarm data of a network awaiting model-building, and performing, by using machine learning and the classification weight value, model-building on the second alarm data to obtain a second alarm tree model, the second alarm data being root-cause relation data.
Proceedings ArticleDOI
15 Jul 2009
TL;DR: In this paper, the authors study the diversity of ways in which the joint computational complexity can behave when all the functions are evaluated on a common input, and prove a result to the effect that the 'obvious' constraints on joint complexity are essentially the only ones.
Abstract: In Direct Sum problems \cite{KRW}, one tries to show that for a given computational model, the complexity of computing a collection $F = \{f_1(x_1), \ldots f_l(x_l)\}$ of finite functions on independent inputs is approximately the sum of their individual complexities. In this paper, by contrast, we study the diversity of ways in which the joint computational complexity can behave when all the $f_i$ are evaluated on a \textit{common} input. We focus on the deterministic decision tree model, with depth as the complexity measure; in this model we prove a result to the effect that the `obvious' constraints on joint computational complexity are essentially the only ones. The proof uses an intriguing new type of cryptographic data structure called a `mystery bin' which we construct using a small polynomial separation between deterministic and unambiguous query complexity shown by Savick\'{y}. We also pose a variant of the Direct Sum Conjecture of \cite{KRW} which, if proved for a single family of functions, could yield an analogous result for models such as the communication model.
Patent
16 Nov 2018
TL;DR: In this article, an accounting method includes the following steps: using Ansj word segmentation technology to extract computerized information in an accounting system and keywords (namely words helpful for subject judgment) in a crowdsourcing platform; constructing a decision tree model; passing keywords of each historical reimbursement document in turn through the three-layer decision tree, analyzing the keywords according to a naive Bayesian model to generate probability of a certain subject; and using the keywords in each historical document to form a set of random non-sequential talking scripts.
Abstract: The invention discloses intelligent accounting technology. An accounting method includes the following steps: using Ansj word segmentation technology to extract computerized information in an accounting system and keywords (namely words helpful for subject judgment) in a crowdsourcing platform; constructing a decision tree model; passing keywords of each historical reimbursement document in turn through the three-layer decision tree model constructed in the previous step; analyzing the keywords according to a naive Bayesian model to generate probability of a certain subject; and using the keywords in each historical document to form a set of random non-sequential talking scripts. According to the technology, a structure is scientific and reasonable, artificial intelligence technology is utilized to automatically generate enterprise accounting-matter and accounting subjects, the artificial intelligence technology is utilized to simulate logic thinking of accounting personnel in judgingthe subjects, automatic subject judgment is realized through a machine, occurrence of errors is reduced, time consumed by accounting work is reduced, and work efficiency is improved. The technology has broad development prospects and promotion values.
Proceedings ArticleDOI
28 May 2021
TL;DR: In this article, a personal credit evaluation model is established to improve the credit evaluation ability of the Internet finance industry to loan individuals, and the independent variables are normalized by zero mean.
Abstract: To improve the credit evaluation ability of the Internet finance industry to loan individuals, a personal credit evaluation model is established. To reduce the influence of experimental data on the results, firstly, the independent variables are normalized by zero mean. Secondly, to solve the collinearity problem, we use principal component analysis to extract key information; Secondly, we use binomial Logit regression to test our model. The result is that compared with the Logit model, the AUC value is 0.6966, and PCA-Logit model has higher classification accuracy, and its AUC value is 0.7620. Therefore, the PCA-Logit model has a better prediction effect, and it is better than the decision tree model. In the case of high-dimensional sparse user data, it can also provide the values of each observation point in the data. It is helpful to establish a relatively more perfect personal credit evaluation system.

Network Information
Related Topics (5)
Cluster analysis
146.5K papers, 2.9M citations
80% related
Artificial neural network
207K papers, 4.5M citations
78% related
Fuzzy logic
151.2K papers, 2.3M citations
77% related
The Internet
213.2K papers, 3.8M citations
77% related
Deep learning
79.8K papers, 2.1M citations
77% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202310
202224
2021101
2020163
2019158
2018121