Customer loss prediction system and method based on machine learning
By obtaining and analyzing the basic and behavioral data of the target customers of the enterprise, using deep learning technology to judge the tendency of customer churn, the problem of predicting customer churn in advance in the existing technology is solved, and the effect of identifying signs of churn in advance and taking measures to reduce the churn rate is achieved. .
Patent Information
- Application Number
- CN202410982704.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-22
AI Technical Summary
The existing technology is difficult to predict customer churn in advance, which causes companies to realize it only after customer churn. The prediction effect is poor, and relying on the personal abilities of individual account managers leads to poor retention and inefficiency.
By obtaining the basic data and behavioral data of the target customers of the enterprise, using deep learning technology for feature extraction and correlation analysis, combining with the classifier to determine whether the customer has a tendency to lose, discover signs of customer churn in advance and take targeted measures.
It realizes the early identification of customer churn signals, reduces customer churn rates, and improves the efficiency and effectiveness of customer relationship maintenance.
Smart Images

Figure CN118967207A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of customer churn prediction, and more specifically, to a customer churn prediction system and method based on machine learning. Background Art
[0002] In today's fiercely competitive market environment, companies usually need to invest a lot of energy in seeking new customers. According to data, the time required to develop a new customer is almost 6 times that of maintaining an old customer. At the same time, the success rate of recommending products or services to old customers is about 50%, while the success rate of recommending to new customers is only 15%. This shows that maintaining existing customer relationships and avoiding customer churn is crucial for companies.
[0003] At present, many domestic companies have attached great importance to the problem of customer churn, but the analysis of customer churn is often unable to predict in advance. Usually, it can only be detected after the customer churn occurs, and the prediction effect is poor. In addition, most companies rely on the personal ability of individual account managers to retain customers, resulting in poor retention effect and low efficiency.
[0004] Therefore, a customer churn prediction system and method based on machine learning is desired. Summary of the invention
[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a customer churn prediction system and method based on machine learning, which first obtains the basic data of the enterprise target customers collected by the database and the enterprise target customer behavior data collected by the database, and then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally uses a classifier to determine whether the target customer has a tendency to churn, so as to detect signs of customer churn in advance, and take targeted retention measures to reduce the customer churn rate.
[0006] According to one aspect of the present application, a customer churn prediction system based on machine learning is provided, which includes:
[0007] The enterprise target customer data acquisition module is used to acquire the basic data of the enterprise target customers collected from the database and the enterprise target customer behavior data collected from the database;
[0008] An enterprise target customer data extraction module, used to extract a target customer basic data text understanding feature vector and an enterprise target customer behavior association feature vector from the enterprise target customer basic data collected from the database and the enterprise target customer behavior data collected from the database;
[0009] The target customer churn tendency judgment module is used to judge whether the target customer has a churn tendency based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector.
[0010] According to another aspect of the present application, a method for predicting customer churn based on machine learning is provided, which comprises:
[0011] Obtaining basic data of target customers of enterprises collected from the database and behavioral data of target customers of enterprises collected from the database;
[0012] Extracting a target customer basic data text understanding feature vector and an enterprise target customer behavior association feature vector from the basic data of the enterprise target customers collected from the database and the enterprise target customer behavior data collected from the database;
[0013] Based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector, it is judged whether the target customer has a tendency to churn.
[0014] Compared with the prior art, the present application provides a customer churn prediction system and method based on machine learning, which first obtains the basic data of the enterprise's target customers collected from the database and the enterprise's target customers' behavior data collected from the database, and then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally uses a classifier to determine whether the target customers have a tendency to churn, so as to detect signs of customer churn in advance, and take targeted retention measures to reduce the customer churn rate. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0016] Figure 1 It is a block diagram of a customer churn prediction system based on machine learning according to an embodiment of the present application.
[0017] Figure 2 It is a block diagram of an enterprise target customer data extraction module in a customer churn prediction system based on machine learning according to an embodiment of the present application.
[0018] Figure 3 It is a block diagram of a customer basic data feature extraction unit in a customer churn prediction system based on machine learning according to an embodiment of the present application.
[0019] Figure 4 4 is a block diagram of a target customer churn tendency judgment module in a customer churn prediction system based on machine learning according to an embodiment of the present application.
[0020] Figure 5 Flow chart of a customer churn prediction method based on machine learning according to an embodiment of the present application.
[0021] Figure 6 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0023] Figure 1 Schematic diagram of a customer churn prediction system based on machine learning in an embodiment of the present application. Figure 1 As shown, according to the machine learning-based customer churn prediction system 100 of the embodiment of the present application, it includes: an enterprise target customer data acquisition module 110, which is used to acquire the basic data of the enterprise target customers collected by the database and the enterprise target customer behavior data collected by the database; an enterprise target customer data extraction module 120, which is used to extract the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector from the enterprise target customer basic data collected by the database and the enterprise target customer behavior data collected by the database; a target customer churn tendency judgment module 130, which is used to judge whether the target customer has a churn tendency based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector.
[0024] In the above-mentioned machine learning-based customer churn prediction system 100, the enterprise target customer data acquisition module 110 is used to obtain the basic data of the enterprise target customers collected by the database and the enterprise target customer behavior data collected by the database. It should be understood that in today's highly competitive market, enterprises usually need to invest a lot of resources and time to acquire new customers. According to data, the time required to develop new customers is almost 6 times that of maintaining old customers. At the same time, the probability of successfully recommending products or services to old customers is about 50%, while the success rate of recommending to new customers is only 15%. This highlights the key impact of maintaining existing customer relationships and avoiding customer churn on the steady development of corporate business. However, although many domestic companies currently attach great importance to the problem of customer churn, they can usually only realize it after the customer has been lost. The ability to predict customer churn is limited and the effect is not good. In addition, most companies rely on the personal ability of individual account managers to retain customers, resulting in unsatisfactory retention effects and inefficiency. Therefore, in the technical solution of the present application, by obtaining the basic data of the enterprise's target customers collected by the database and the enterprise's target customers' behavior data collected by the database, and combining it with deep learning technology, it is judged whether the target customers have a tendency to churn, thereby reducing the customer churn rate by identifying the signals of customer churn in advance and implementing targeted retention measures.
[0025] Specifically, the basic data and behavioral data of the target customers of an enterprise collected by the database are obtained in order to deeply understand customers, optimize services, and predict key business activities such as customer churn. Among them, basic data usually includes basic information of customers, such as name, contact information, company name, address, etc., which helps to establish customer files and identify the identity characteristics of each customer. In addition, basic data also covers customer preferences, purchase history, transaction records, etc., which are essential for personalized marketing and customized services. Compared with basic data, the behavioral data of the target customers of an enterprise are more dynamic and specific. These data record every interaction between customers and the enterprise, including website browsing history, purchase behavior, customer service conversation content, product usage, etc. By analyzing these behavioral data, enterprises can understand customers' behavior patterns, preference changes, and their actual feelings about products or services. Based on these data, churn prediction and customer retention are carried out. By analyzing customer behavior changes and early warning signals, enterprises can identify potential churn risks in advance and take targeted retention measures, such as personalized coupons, customized service plans or exclusive customer care plans, thereby effectively reducing customer churn rates and maintaining good customer relationships.
[0026] In the above-mentioned machine learning-based customer churn prediction system 100, the enterprise target customer data extraction module 120 is used to extract the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector from the basic data of the enterprise target customers collected by the database and the enterprise target customer behavior data collected by the database. It should be understood that combining the basic data feature vector and the behavior data association feature vector can provide more comprehensive and detailed customer insights. For example, combining the age in the basic data and the purchasing preferences in the behavior data, an enterprise can customize promotional activities for customers in a specific age group to improve the effectiveness and return on investment of marketing activities. In addition, the behavior association feature vector can also help enterprises identify potential high-value customers, respond to their needs in a timely manner and provide personalized services, thereby enhancing customer loyalty and satisfaction.
[0027] Figure 2 FIG. 1 is a block diagram of an enterprise target customer data extraction module in a customer churn prediction system based on machine learning according to an embodiment of the present application. Figure 2 As shown, in a specific embodiment of the present application, the enterprise target customer data extraction module 120 includes: a customer basic data feature extraction unit 121, which is used to perform feature extraction on the basic data of the enterprise target customers collected from the database to obtain the target customer basic data text understanding feature vector; a customer behavior data feature extraction unit 122, which is used to perform feature extraction on the enterprise behavior data of the enterprise target customers collected from the database to obtain the enterprise target customer behavior association feature vector.
[0028] It should be understood that feature extraction can help companies identify and capture important features and patterns in customer data. The basic data of target customers may contain a lot of information, such as the customer's age, gender, geographic location, purchase history, transaction frequency, etc. Through feature extraction, the most relevant and distinguishing features can be extracted from these data, such as converting the customer's age into age group code, converting the geographic location into latitude and longitude coordinates, and converting the purchase history into frequency or amount statistics. These features help to build detailed profiles of customers, so as to better understand the customer's personalized needs and behavior patterns. In addition, feature extraction can also reduce data dimensions and complexity, and improve the efficiency of data processing and analysis. The original data set often contains a lot of redundant information or unnecessary details. Feature extraction can streamline the data set and retain the most informative and predictive features, thereby simplifying the subsequent analysis and modeling process. This not only helps to reduce the consumption of computing resources, but also improves the training speed and prediction accuracy of the model.
[0029] Furthermore, the enterprise behavior data of the target customers of the enterprise collected by the database is subjected to feature extraction, aiming to extract the most representative and predictive features from these data, so as to analyze and predict the customer's behavior patterns, trends and preferences. This process is an important step in data-driven decision-making, which can help enterprises better understand and respond to customer needs, optimize business processes and improve service quality. Among them, the behavior data of the target customers of the enterprise usually includes information such as customer purchase history, visit frequency, product usage, service feedback, etc. Through feature extraction, the most critical features can be extracted from these complex behavior data, such as purchase frequency, statistical characteristics of purchase amount, most commonly used products or services, average service response time, etc. These feature vectors can reflect the customer's activity, loyalty, stability of purchase behavior, and preference for products or services. Here, feature extraction can also help enterprises identify and predict customer behavior trends and changes. By analyzing the feature vectors of behavioral data, enterprises can find out whether customers' consumption habits have changed, whether there are potential signs of churn, which products or services are most popular, etc. These insights are crucial for developing personalized marketing strategies, improving customer experience and increasing customer satisfaction.
[0030] Figure 3 FIG. 1 is a block diagram of a customer basic data feature extraction unit in a customer churn prediction system based on machine learning according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the customer basic data feature extraction unit 121 includes: a basic data text encoding preprocessing subunit 1211, which is used to perform text encoding preprocessing on the basic data of the enterprise target customers collected from the database to obtain a target customer basic data vector sequence; a basic data text understanding subunit 1212, which is used to pass the target customer basic data vector sequence through a basic data vector sequence semantic understanding Bi-LSTM model to obtain the target customer basic data text understanding feature vector.
[0031] It should be understood that text encoding preprocessing can convert text descriptions, classification information or other non-numerical data in customer basic data into digital vectors that can be understood and processed by computers. For example, the customer's geographic location information is encoded into longitude and latitude coordinates, the customer's occupational information is converted into industry classification codes, and the customer's product preference description is converted into binary or multidimensional vectors. These conversions make the data easier to perform mathematical operations and model training, thereby helping companies understand and predict customer behavior. The resulting target customer basic data vector sequence can be used to build customer portraits or perform customer segmentation analysis. Through numerical vector representation, companies can classify and group customers based on their common characteristics. For example, customers with similar purchase histories or behavior patterns can be clustered together through clustering algorithms, thereby providing companies with more accurate target markets and personalized marketing strategies.
[0032] Furthermore, the target customer basic data vector sequence is processed by the basic data vector sequence semantic understanding Bi-LSTM model, aiming to extract more advanced semantic feature representations from the data using a deep learning model. This method combines natural language processing and machine learning techniques, and can effectively convert numerical customer data into feature vectors with more semantic understanding capabilities. Among them, the Bi-LSTM model (bidirectional long short-term memory network), as a sequence model, is particularly suitable for processing time series or text sequence data. It can capture long-range dependencies and semantic information in the data, and effectively learn contextual features in the data by considering both the past and future information of the sequence. In the context of the target customer basic data, the Bi-LSTM model can understand the temporal relationship and semantic content in the customer information, thereby more comprehensively expressing the customer's characteristics and behavior patterns. The target customer basic data text understanding feature vectors obtained by the Bi-LSTM model have high information richness and abstraction capabilities. These feature vectors not only contain the numerical representation of the original data, but also integrate the semantic and contextual information of the text. For example, for a customer's purchase history, behavior pattern or preference description, Bi-LSTM can convert this information into a more specific and in-depth feature vector, reflecting the customer's personalized characteristics and change trends in multiple dimensions. Specifically, the basic data vector sequence semantic understanding Bi-LSTM model adds input gates, output gates and forget gates to enable the weights of the neural network to self-update. When the network model parameters are fixed, the weight scales of different channels can be changed dynamically, thereby avoiding the problem of gradient vanishing or gradient expansion.
[0033] In a specific embodiment of the present application, the basic data text encoding preprocessing subunit 1211 includes: passing the basic data of the enterprise target customers collected from the database through a target customer basic data semantic context encoder including an embedding layer to obtain a plurality of target customer basic data semantic feature vectors; arranging the plurality of target customer basic data semantic feature vectors to obtain the target customer basic data vector sequence.
[0034] It should be understood that the target customer basic data usually contains information of various dimensions, such as the customer's personal information, historical transactions, behavioral preferences, etc. This information is often unstructured or semi-structured and needs to be converted by a semantic context encoder so that the computer can understand and process it. The role of the embedding layer here is to map the original data to a low-dimensional vector space, and by learning the relationship and similarity between the data, the characteristics of each customer can be represented in a more informative and semantically understandable way. In the technical solution of the present application, the semantic context encoder usually adopts a deep learning model, such as a neural network containing an embedding layer, especially a model suitable for processing sequence data (such as LSTM, GRU, etc.). These models can learn the potential semantic features in the data while retaining the data sequence structure. For example, for the customer's purchase history and product preferences, the semantic context encoder can extract representative feature vectors that reflect the evolution trend of the customer's purchasing habits, preference changes and behavior patterns. In addition, the semantic feature vectors of multiple target customer basic data obtained by the embedding layer and the semantic context encoder can support more refined customer analysis and prediction. These vectors can not only provide static attribute information of customers, such as age and gender, but also capture the dynamic changes of customers in time and their adaptability in situations. For example, based on these vectors, enterprises can achieve a comprehensive understanding of the customer life cycle, thereby optimizing customer relationship management strategies, improving customer service and the effectiveness of personalized recommendation systems. Specifically, the basic data of the enterprise's target customers collected by the database is segmented to obtain a basic data word sequence; the embedding layer of the target customer basic data semantic context encoder containing the embedding layer is used to map each basic data word in the basic data word sequence to a basic data word embedding vector to obtain a sequence of basic data word embedding vectors; the converter-based Bert model of the target customer basic data semantic context encoder containing the embedding layer is used to perform global context semantic encoding on the sequence of basic data word embedding vectors to obtain multiple target customer basic data semantic feature vectors.
[0035] Furthermore, the semantic feature vectors of multiple target customer basic data are arranged in order to effectively organize and represent the complex and multi-dimensional feature information of each customer into a continuous data sequence for subsequent analysis, modeling and application. Here, the semantic feature vectors of multiple target customer basic data usually contain various key features extracted from customer data. These features may cover multiple aspects such as personal attributes, behavior patterns, purchase preferences, social interactions, etc. of customers. By arranging these feature vectors, the feature information of each customer can be organized in a certain order or time series to form a customer-level data sequence. In this way, it is helpful to retain the time order or correlation of customer data, so as to better reflect the changing trend of customer behavior and preferences. For example, if the feature vectors of the time series are extracted based on the customer's historical purchase behavior, a time series can be formed by arranging these vectors to show the customer's purchase behavior and its changes at different time points. This serialized representation helps to analyze the dynamic evolution of customer behavior, identify long-term and short-term behavior patterns, and formulate personalized marketing and service strategies accordingly.
[0036] In a specific embodiment of the present application, the customer behavior data feature extraction unit 122 includes: segmenting the enterprise target customer enterprise behavior data collected by the database to obtain multiple enterprise target customer behavior data items; passing the multiple enterprise target customer behavior data items through an enterprise target customer behavior multi-scale feature extractor to obtain the enterprise target customer behavior associated feature vector.
[0037] It should be understood that the behavioral data of the target customers of an enterprise covers many aspects, such as customer transaction records, online activities, product usage, feedback, etc. These data usually exist in text or structured formats, and can be converted into data items with clear semantics through word segmentation. For example, a text containing a customer's purchase record is segmented into data items such as goods, quantity, price, etc., or a customer's online behavior is decomposed into separate action items such as browsing, clicking, and purchasing. Word segmentation can help companies analyze and understand customer behavior characteristics more carefully. By decomposing complex behavioral data into multiple data items, customer behavior patterns and preferences can be captured more accurately. For example, for e-commerce platforms, after the customer's purchase behavior is segmented, the customer's purchase frequency, purchase preferences (such as categories, brands), shopping time, etc. can be analyzed, so as to optimize product recommendations and promotion strategies, and improve sales conversion rates and customer satisfaction.
[0038] Furthermore, the behavior data of target customers of an enterprise usually contains information of multiple types and time scales. For example, a customer's transaction record may involve detailed information of each transaction, purchase time, purchase frequency, etc.; a customer's online behavior may include browsing history, click patterns, retention time, etc. Through the multi-scale feature extractor of target customer behavior of an enterprise, these multi-dimensional data items can be processed simultaneously, and different levels of features can be extracted from them, such as basic features (such as purchase amount, number of clicks), time series features (such as purchase frequency change trend), sequence pattern features (such as common purchase sequence patterns), etc. The application of multi-scale feature extractors enables enterprises to conduct in-depth analysis and modeling at different data levels. By extracting feature vectors at different levels, enterprises can more comprehensively describe and understand the behavioral relevance of customers. For example, combining basic features and time series features, customers' long-term purchasing habits and seasonal changes can be analyzed; combining sequence pattern features, customers' typical behavior paths and decision-making processes can be identified, and then customers' future behaviors and demand changes can be accurately predicted. Specifically, the enterprise target customer behavior multi-scale feature extractor includes: a first convolution layer, a second convolution layer parallel to the first convolution layer, and a cascade layer connected to the first convolution layer and the second convolution layer, wherein the first convolution layer uses a one-dimensional convolution kernel with a first scale, and the second convolution layer uses a one-dimensional convolution kernel with a second scale. More specifically, the first convolution layer of the enterprise target customer behavior multi-scale feature extractor is used to perform one-dimensional convolution encoding on the multiple enterprise target customer behavior data items to obtain a first-scale feature vector; the second convolution layer of the multi-scale neighborhood feature extraction module is used to perform one-dimensional convolution encoding on the multiple enterprise target customer behavior data items to obtain a second-scale feature vector; the first-scale feature vector and the second-scale feature vector are cascaded to obtain the enterprise target customer behavior association feature vector.
[0039] In the above-mentioned machine learning-based customer churn prediction system 100, the target customer churn tendency judgment module 130 is used to judge whether the target customer has a churn tendency based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector. It should be understood that the target customer basic data text understanding feature vector usually contains the customer's static attribute information and the semantic features of the text content. These feature vectors may cover aspects such as the customer's personal profile, historical transaction information, and social interaction. For example, the feature vector extracted from the customer's registration information and social media interaction can reflect the customer's age, geographic location, interests and hobbies and other key attributes. The enterprise target customer behavior association feature vector focuses on the customer's behavior pattern and interaction trajectory. These feature vectors usually involve customer purchase frequency, usage habits, product preference changes, service complaint feedback and other behavioral data. By analyzing these vectors, the changes and reactions of customers in the process of using products or services can be captured, such as the purchase activity in the recent period, the increase or decrease of service complaints, and the frequency of interaction with the brand. Based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector, the churn tendency judgment can not only help enterprises to timely identify potential churn customers, but also effectively optimize customer relationship management strategies, improve customer retention rate and overall business performance. This data-driven approach continuously optimizes enterprises' understanding and response capabilities to customer behavior, providing important support for sustained advantages in market competition.
[0040] Figure 4 FIG. 1 is a block diagram of a target customer churn tendency judgment module in a customer churn prediction system based on machine learning according to an embodiment of the present application. Figure 4 As shown, in a specific embodiment of the present application, the target customer churn tendency judgment module 130 includes: a target customer feature fusion unit 131, which is used to fuse the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector to obtain a target customer churn tendency feature vector; a target customer feature optimization unit 132, which is used to perform backward correlation perception on the target customer churn tendency feature vector based on the class regression domain parameter space to obtain an optimized target customer churn tendency feature vector; a target customer churn tendency generation unit 133, which is used to pass the optimized target customer churn tendency feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether the target customer has a churn tendency.
[0041] It should be understood that the fusion of the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector can achieve a comprehensive analysis of customers by integrating static attributes and dynamic behavior features. Among them, the static attribute features provide basic background information of customers, while the dynamic behavior features reveal the actual patterns and trends of customers' interactions with products or services. Comprehensive analysis of these two types of features can more comprehensively understand the driving factors behind customers' behavior. In addition, based on the prediction results of the churn propensity feature vector, enterprises can formulate personalized marketing and maintenance strategies. For example, for customers predicted to be at high risk of churn, customized promotions can be pushed or service quality can be improved to enhance customer satisfaction and retention rate, thereby providing enterprises with a panoramic view of in-depth insights into customers, helping to predict and respond to customer churn risks, and thus achieving continuous optimization of customer relationships and sustainable growth of business.
[0042] In particular, the target customer churn tendency feature vector is subjected to backward correlation perception based on the class regression domain parameter space to obtain an optimized target customer churn tendency feature vector, including: multiplying the target customer churn tendency feature vector with the classification weight matrix of the classifier to obtain a first intermediate target customer churn tendency feature vector; using the concat function to process the target customer churn tendency feature vector and the first intermediate target customer churn tendency feature vector to obtain a second intermediate target customer churn tendency feature vector; adding the target customer churn tendency feature vector and the first intermediate target customer churn tendency feature vector by position to obtain a third intermediate target customer churn tendency feature vector; multiplying the first weight matrix by the second intermediate target customer churn tendency feature vector plus the first bias vector and then passing through the sigmoid function to obtain a first activation value; The matrix is multiplied by the third intermediate target customer churn tendency feature vector plus the second bias vector and then passed through the sigmoid function to obtain a second activation value; the mean of the first activation value and the second activation value is calculated to obtain the activation mean; the difference between one and the activation mean is calculated, and the difference is used as the first weighting coefficient and the activation mean is used as the second weighting coefficient, and the second intermediate target customer churn tendency feature vector and the target customer churn tendency feature vector are weighted by position to obtain a fourth intermediate target customer churn tendency feature vector; each eigenvalue of the backward anchoring reference vector is subjected to an exponential operation with a natural constant as the base to obtain a fifth intermediate target customer churn tendency feature vector; the fourth intermediate target customer churn tendency feature vector is subtracted by the fifth intermediate target customer churn tendency feature vector by position and then passed through the ReLU function to obtain the optimized target customer churn tendency feature vector.
[0043] In particular, in the technical solution of the present application, the data set may contain customer data from different sources with different characteristics. The distribution of these data in the feature space may be very different, resulting in inconsistent distribution of the target customer churn tendency feature vector. The target customer churn tendency feature vector may contain some features that are not related to the target task (customer retention). These irrelevant features will make the feature space complicated and reduce the consistency of the manifold. If the manifold geometric consistency of the overall feature distribution of the target customer churn tendency feature vector is poor, this may mean that the feature vector is unevenly distributed in the high-dimensional space, or the correlation between the features is not strong. When the target customer churn tendency feature vector is inconsistently distributed in the high-dimensional space, the classifier may have a long-range distribution regression bias when classifying. This means that when the classifier processes samples far away from the decision boundary, due to the inconsistency of the feature space, it may cause a deviation in the classification decision. The long-range distribution regression bias will reduce the accuracy of the classification results when the classifier processes areas where the feature vectors are sparsely distributed. This is because the classifier may not have enough training data to accurately learn the decision boundaries of these areas. Based on this, in the technical solution of the present application, backward correlation perception is performed on the target customer churn tendency feature vector based on the class regression domain parameter space to obtain an optimized target customer churn tendency feature vector.
[0044] The target customer churn tendency feature vector is subjected to backward correlation perception based on the regression domain parameter space to obtain an optimized target customer churn tendency feature vector, including: performing backward correlation perception based on the regression domain parameter space on the target customer churn tendency feature vector according to the following optimization formula, wherein the optimization formula is:
[0045]
[0046]
[0047] Among them, v c represents the target customer churn tendency feature vector, M represents the classification weight matrix of the classifier, represents matrix multiplication, concat represents the cascade function, V r is the backward anchor reference vector, W1 represents the first weight matrix, b1 represents the first bias vector, t1 represents the first activation value, W2 represents the second weight matrix, b2 represents the second bias vector, t2 represents the second activation value, sigmoid represents the logistic function, represents positional subtraction, ReLU represents the linear rectification function, exp represents the natural exponential function, and V′ represents the optimized target customer churn tendency feature vector.
[0048] That is, in the technical solution of the present application, the manifold geometric consistency of the overall feature distribution of the target customer churn tendency feature vector is poor, resulting in a remote distribution regression deviation across classifiers when it is classified through a classifier, affecting the accuracy of the classification result. Therefore, in the technical solution of the present application, the target customer churn tendency feature vector is subjected to backward correlation perception based on the class regression domain parameter space, and the classification weight matrix of the classifier is used to perform an auxiliary description of the attribute distribution of the target customer churn tendency feature vector to support the improved target customer churn tendency feature vector for the different distance feature descriptions of the classification weight matrix of the classifier to the descriptiveness of the category probability of the preset classification, wherein the backward anchor reference vector is used as an offset and activated by an activation operation to maintain the reinforcement of the distribution description dependency with a positive effect, so that the manifold geometric consistency of the overall attribute distribution of the target customer churn tendency feature vector can be significantly improved, thereby reducing the class probability distribution regression deviation of the target customer churn tendency feature vector when it passes through the classifier, so as to improve the accuracy of the classification result.
[0049] Furthermore, the optimized target customer churn tendency feature vector is passed through a classifier to obtain a classification result, mainly to achieve more accurate and actionable churn prediction and customer management strategy formulation. Here, by optimizing the target customer churn tendency feature vector, the static attributes and dynamic behaviors of the customer have been comprehensively considered, and these features can effectively reflect the possible churn risk of the customer. However, the feature vector itself is not enough to make a decision directly, because the feature vector may contain complex data and patterns, and a system that can understand and process this information is required to provide actual prediction results. The classifier learns the relationship pattern between the feature vector and the actual churn situation through the training phase and establishes a prediction model. This model can identify patterns or feature combinations that may cause churn from the customer's feature vector, thereby predicting the churn tendency of future customers. For example, the model may find that a specific feature combination such as a decrease in purchase frequency, an increase in complaints, or a change in product usage is significantly associated with customer churn. Using the classification results obtained by the classifier, the company can promptly identify the target customer group with a tendency to churn, and take targeted measures to intervene and retain them. This includes but is not limited to personalized customer service, preferential promotions, customized product recommendations and other measures to improve the satisfaction and loyalty of these customers and reduce the risk of churn. Specifically, the optimized target customer churn tendency feature vector is fully connected encoded using the fully connected layer of the classifier to obtain a fully connected encoded feature vector; the fully connected encoded feature vector is input into the Softmax classification function of the classifier to obtain probability values of the optimized target customer churn tendency feature vector belonging to various classification labels, wherein the classification labels include those for indicating that the target customer has a churn tendency and that the target customer does not have a churn tendency; and the classification label corresponding to the largest of the probability values is determined as the classification result.
[0050] In summary, the embodiment of the present application first obtains the basic data of the enterprise target customers collected by the database and the enterprise target customers behavior data collected by the database, and then uses deep learning technology to perform feature extraction and correlation analysis on the two, and finally uses a classifier to determine whether the target customers have a tendency to churn, so as to discover signs of customer churn in advance, and take targeted retention measures to reduce customer churn rate.
[0051] As described above, the customer churn prediction system 100 based on machine learning according to the embodiment of the present application can be implemented in various terminal devices. In one example, the customer churn prediction system 100 based on machine learning can be integrated into the terminal device as a software module and / or a hardware module. For example, the customer churn prediction system 100 based on machine learning can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the customer churn prediction system 100 based on machine learning can also be one of the many hardware modules of the terminal device.
[0052] Alternatively, in another example, the machine learning-based customer churn prediction system 100 and the terminal device may also be separate devices, and the machine learning-based customer churn prediction system 100 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.
[0053] Figure 5 Flow chart of the method for predicting customer churn based on machine learning according to an embodiment of the present application. Figure 5 As shown, according to the customer churn prediction method based on machine learning according to the embodiment of the present application, it includes: S110, acquiring the basic data of the enterprise target customers collected by the database and the enterprise target customer behavior data collected by the database; S120, extracting the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector from the enterprise target customer basic data collected by the database and the enterprise target customer behavior data collected by the database; S130, judging whether the target customer has a tendency to churn based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector.
[0054] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned customer churn prediction method based on machine learning have been referred to above. Figures 1 to 4 The description of the machine learning-based customer churn prediction system has been introduced in detail, and therefore, its repeated description will be omitted.
[0055] Below, reference Figure 6 To describe an electronic device according to an embodiment of the present application.
[0056] An embodiment of the present application provides an electronic device. Figure 6 is a block diagram of an electronic device according to an embodiment of the present application.
[0057] like Figure 6As shown, the electronic device 10 includes an input device 11, an input interface 12, a central processing unit 13, a memory 14, an output interface 15, an output device 16, and a bus 17. The input interface 12, the central processing unit 13, the memory 14, and the output interface 15 are connected to each other through the bus 17, and the input device 11 and the output device 16 are connected to the bus 17 through the input interface 12 and the output interface 15, respectively, and then connected to other components of the electronic device 10.
[0058] Specifically, the input device 11 receives input information from the outside and transmits the input information to the central processing unit 13 through the input interface 12; the central processing unit 13 processes the input information based on the computer executable instructions stored in the memory 14 to generate output information, temporarily or permanently stores the output information in the memory 14, and then transmits the output information to the output device 16 through the output interface 15; the output device 16 outputs the output information to the outside of the electronic device 10 for user use.
[0059] In one embodiment, Figure 6 The electronic device 10 shown can be implemented as a network device, which may include: a memory configured to store programs; a processor configured to run the programs stored in the memory to execute any one of the customer churn prediction system methods based on machine learning described in the above embodiments.
[0060] According to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network, and / or installed from a removable storage medium.
[0061] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.
[0062] It can be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto.
Claims
1. A customer churn prediction system based on machine learning, characterized in that: include: The enterprise target customer data acquisition module is used to acquire the basic data of the enterprise target customers collected from the database and the enterprise target customer behavior data collected from the database; An enterprise target customer data extraction module, used to extract a target customer basic data text understanding feature vector and an enterprise target customer behavior association feature vector from the enterprise target customer basic data collected from the database and the enterprise target customer behavior data collected from the database; The target customer churn tendency judgment module is used to judge whether the target customer has a churn tendency based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector.
2. The customer churn prediction system based on machine learning according to claim 1, characterized in that: The enterprise target customer data extraction module includes: A customer basic data feature extraction unit, used for extracting features from the basic data of the enterprise target customers collected from the database to obtain a text understanding feature vector of the target customer basic data; The customer behavior data feature extraction unit is used to extract features from the enterprise target customer enterprise behavior data collected from the database to obtain the enterprise target customer behavior associated feature vector.
3. The customer churn prediction system based on machine learning according to claim 2, characterized in that: The customer basic data feature extraction unit includes: A basic data text encoding preprocessing subunit is used to perform text encoding preprocessing on the basic data of the target customers of the enterprise collected from the database to obtain a target customer basic data vector sequence; The basic data text understanding subunit is used to obtain the target customer basic data text understanding feature vector by passing the target customer basic data vector sequence through the basic data vector sequence semantic understanding Bi-LSTM model.
4. The customer churn prediction system based on machine learning according to claim 3, characterized in that: The basic data text encoding preprocessing subunit includes: The basic data of the target customers of the enterprise collected from the database is passed through a target customer basic data semantic context encoder including an embedding layer to obtain a plurality of target customer basic data semantic feature vectors; The plurality of target customer basic data semantic feature vectors are arranged to obtain the target customer basic data vector sequence.
5. The customer churn prediction system based on machine learning according to claim 4, characterized in that: The customer behavior data feature extraction unit comprises: Segmenting the enterprise target customer enterprise behavior data collected from the database to obtain multiple enterprise target customer behavior data items; The plurality of enterprise target customer behavior data items are passed through an enterprise target customer behavior multi-scale feature extractor to obtain the enterprise target customer behavior associated feature vector.
6. The customer churn prediction system based on machine learning according to claim 5, characterized in that: The target customer churn tendency judgment module includes: A target customer feature fusion unit, used for fusing the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector to obtain a target customer churn tendency feature vector; A target customer feature optimization unit, used for performing backward correlation perception on a target customer churn tendency feature vector based on a class regression domain parameter space to obtain an optimized target customer churn tendency feature vector; The target customer churn tendency generating unit is used to pass the optimized target customer churn tendency feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether the target customer has a churn tendency.
7. The customer churn prediction system based on machine learning according to claim 6, characterized in that: The target customer feature optimization unit comprises: Multiplying the target customer churn tendency feature vector by a classification weight matrix of a classifier to obtain a first intermediate target customer churn tendency feature vector; Using a concat function to process the target customer churn tendency feature vector and the first intermediate target customer churn tendency feature vector to obtain a second intermediate target customer churn tendency feature vector; Add the target customer churn tendency feature vector and the first intermediate target customer churn tendency feature vector by position to obtain a third intermediate target customer churn tendency feature vector; The first weight matrix is multiplied by the second intermediate target customer churn tendency feature vector and then added to the first bias vector and then passed through the sigmoid function to obtain a first activation value; The second weight matrix is multiplied by the third intermediate target customer churn tendency feature vector plus the second bias vector and then passed through the sigmoid function to obtain a second activation value; Calculating a mean of the first activation value and the second activation value to obtain an activation mean; Calculate a difference value minus the activation mean, and use the difference value as a first weighting coefficient and the activation mean value as a second weighting coefficient to weight the second intermediate target customer churn tendency feature vector and the target customer churn tendency feature vector by position to obtain a fourth intermediate target customer churn tendency feature vector; Performing an exponential operation with a natural constant as the base on each eigenvalue of the backward anchor reference vector to obtain a fifth intermediate target customer churn tendency eigenvector; The fourth intermediate target customer churn tendency feature vector is subtracted from the fifth intermediate target customer churn tendency feature vector by position and then passed through a ReLU function to obtain an optimized target customer churn tendency feature vector.
8. The customer churn prediction system based on machine learning according to claim 7, characterized in that: The target customer churn tendency generating unit comprises: Using the fully connected layer of the classifier to perform fully connected encoding on the optimized target customer churn tendency feature vector to obtain a fully connected encoded feature vector; Inputting the fully connected encoded feature vector into the Softmax classification function of the classifier to obtain probability values of the optimized target customer churn tendency feature vector belonging to each classification label, wherein the classification label includes a label for indicating that the target customer has a churn tendency and the target customer does not have a churn tendency; and The classification label corresponding to the largest probability value among the probability values is determined as the classification result.
9. A customer churn prediction method based on machine learning, characterized in that: include: Obtaining basic data of target customers of enterprises collected from the database and behavioral data of target customers of enterprises collected from the database; Extracting a target customer basic data text understanding feature vector and an enterprise target customer behavior association feature vector from the basic data of the enterprise target customers collected from the database and the enterprise target customer behavior data collected from the database; Based on the target customer basic data text understanding feature vector and the enterprise target customer behavior association feature vector, it is judged whether the target customer has a tendency to churn.
10. The method for predicting customer churn based on machine learning according to claim 9, characterized in that: Extracting a target customer basic data text understanding feature vector and an enterprise target customer behavior association feature vector from the enterprise target customer basic data collected from the database and the enterprise target customer behavior data collected from the database includes: Performing feature extraction on the basic data of the enterprise target customers collected from the database to obtain a text understanding feature vector of the target customer basic data; Feature extraction is performed on the enterprise target customer enterprise behavior data collected from the database to obtain the enterprise target customer behavior related feature vector.
Citation Information
Patent Citations
Customer loss prediction method and device
CN105069534A
Learning method and system for international finance and financial metrology teaching
CN115222566A
Intelligent energy-saving control system and method based on central air conditioner
CN117029191A
Intelligent business data processing method and system based on feature fusion
CN117522449A
Generating capacity peak and valley self-adaptive control method and model training method of offshore wind turbine unit
CN117977703A
Cited By
Full-automatic filling and tail sealing machine and method thereof
CN118735892A
