The invention provides a high potential user buying intention prediction method based on big data user behavior analysis. The high potential user buying intention prediction method comprises the following steps: 101 data preprocessing: the historical behavior data set of the e-commerce user is preprocessed; 102 sample defining and marking: samples are constructed with the interacted user product pairs to act as the keywords according to the historical consumption behavior of the user; 103 division of a training set and a test set: the historical data are divided into the training set and the test set by using a time window division method; 104 feature construction: feature engineering construction of the historical behavior data of the user is performed; and 105 algorithm design and implementation: feature selection of the feature group and unbalanced data processing of the data set are performed and then the final result of two-layer model iterative learning algorithm prediction is put forward. The prediction model is established on the basis of the historical behavior data of the e-commerce user of the time span of 45 days so that whether the user places an order of the commodityin the candidate commodity set P in the following 5 days can be predicted.

High potential user buying intention prediction method based on big data user behavior analysis

The invention discloses a default user risk prediction method based on big data finance The method comprises: 102 dividing the training set data according to the historical behavior, and verifying the set data; 103 performing feature engineering operation on user history data; 104 carrying out feature selection on a sample set which is completed by construct features; 105, establishing a plurality of machine learning models, and performing model fusion operation; 106 based on the user's historical behavior data, the model being used to predict whether the user will overdue repayment in the next month or not The invention mainly pretreats and analyzes the historical data of users, extracts features, selects features, establishes a plurality of machine learning models, predicts whether users will overpay in the next month according to the consumer behavior data of users on the Internet, and provides more accurate risk control service for subdividing crowds in the financial field

Forecasting method of default user risk based on big data finance

The invention belongs to the technical field of intelligent distribution, and relates to an O2O coupon distribution method and system based on big data analysis. Firstly, the obtained data in a certain period of time is divided, and verification set data corresponding to the period of time are respectively established; then abstracting and extracting the features from the data according to the declared or defined features; secondly, feature merging is carried out to remove identical data, and the data is normalized; the feature sets other than the corresponding feature sets of the test set aretagged, and the extracted feature sets are connected to form a general feature set, and the feature matrix conforming to the requirements of the XGBoost model is constructed; then the XGBoost model is used to predict the coupons; finally, the critical value is set and the distribution prompt is given according to the critical value to realize the distribution of coupons. ,In the invention, data coverage is wider, reducing the merchant's marketing costs, optimizing the consumer experience, and optimizing the transaction.

An O2O coupon distribution method and system based on big data analysis

The invention provides an intelligent temperature control adjusting method based on big data. The intelligent temperature control adjusting method based on the big data comprises the steps of data pretreatment, characteristic engineering construction operation, establishment of a plurality of machine learning models and the like. According to the intelligent temperature control adjusting method based on the big data, information interaction of intelligent homes is utilized to collect user data, the user data is analyzed, so that the goals of ventilation, adjusting user comfort temperature, ensuring indoor air quality and energy conservation and emission reduction are realized, and the social value of the energy conservation and emission reduction is greatly realized.

Intelligent temperature control adjusting method based on big data

The embodiment of the invention provides a text classification method and device. The method comprises the steps that all sample texts in a sample set are preprocessed to obtain category information and a segmented word corpus of all the sample texts; the sample set is divided into a test set and a training set by summarizing the category information and the segmented word corpus of all the sampletexts in the sample set; and text classification is performed on all the sample texts in the sample set through the test set and the training set. According to the embodiment, all the sample texts inthe sample set are preprocessed to obtain the category information and the segmented word corpus of all the sample texts; the sample set is divided into the test set and the training set by summarizing the category information and the segmented word corpus of all the sample texts in the sample set; text classification is performed on all the sample texts in the sample set through the test set andthe training set; and classification of big data texts is realized in combination with an R language and Hadoop.

Text classification method and device

The invention requests to protect a commodity recommendation method based on mobile electronic commerce of big data. The method comprises the following steps that: 101: carrying out a preprocessing operation on the historical behavior data of a user; 102: according to behavior time, carrying out a data division operation on the historical data of the user; 103: marking the historical behavior dataof the user; 104: carrying out a feature engineering construction operation on the historical data of the user; 105: establishing a plurality of machine learning models, and carrying out a model fusion operation; and 106: through an established model, according to the behavior data of the user, predicting whether the user purchases a certain commodity in one future day or not. By use of the method, the historical data of the user is preprocessed and analyzed to extract features, the plurality of machine learning models are established so as to predict a probability for the user to purchase the certain commodity in one future day, and accuracy for a merchant to recommend commodities to the user is improved.

Commodity recommendation method based on mobile electronic commerce of big data

The invention protects an O2O coupon usage big data prediction method. The method comprises the steps that 101, a historical consumption dataset of a user is subjected to preprocessing operation; 102, the historical consumption dataset of the user is marked, and a training set and a prediction set are divided and constructed; 103, the historical consumption dataset of the user is subjected to feature engineering construction; 104, feature selection and processing of unbalanced data are performed; 105, the data is subjected to multi-classifier integrated learning; and 106, coupon usage of the user is predicted through an established model according to historical consumption data of the user, and serving of an O2O coupon is optimized. According to the method, a prediction model is established mainly by processing the user consumption data and performing multi-classifier integrated learning on the data, therefore, the coupon usage of the user in the future is predicted, and serving of the O2O coupon is optimized.

O2O coupon usage big data prediction method

The invention discloses an MPI-based ML-KNN multi-tag Chinese text classification method, and relates to a multi-tag classification algorithm in text classification and machine learning. In order to solve the large-scale text classification problem and the solving optimization problem in specific implementation of an ML-KNN algorithm, the calculation time and the space overhead are controlled. According to the technical scheme, the parallelization of Chinese text data preprocessing, feature extraction, the ML-KNN algorithm and classification is realized by adopting MPI programming. Compared with a conventional serial multi-tag Chinese text classification method, the multi-tag Chinese text classification efficiency is greatly improved; under the condition of a fixed data amount, the algorithm efficiency is improved with increment of calculation resources (the number of processes) in general; and it is worth mentioning that in the MPI-based ML-KNN parallelization step, a data set can be divided by not only taking a sample as a unit but also taking a feature as a unit, so that the method has the better advantage in processing high-dimensional text data.

Shao Shuai

Papers

Commodity recommendation method based on mobile electronic commerce of big data

O2O coupon usage big data prediction method

MPI-based ML-KNN multi-tag Chinese text classification method