In the telco industry, attracting new customers is no longer a good strategy since the cost of retaining existing customers is much lower. Churn management becomes instrumental in the telco industry. As there is limited study combining churn prediction and customer segmentation, this paper aims to propose an integrated customer analytics framework for churn management. There are six components in the framework, including data pre-processing, exploratory data analysis (EDA), churn prediction, factor analysis, customer segmentation, and customer behaviour analytics. This framework integrates churn prediction and customer segmentation process to provide telco operators with a complete churn analysis to better manage customer churn. Three datasets are used in the experiments with six machine learning classifiers. First, the churn status of the customers is predicted using multiple machine learning classifiers. Synthetic Minority Oversampling Technique (SMOTE) is applied to the training set to deal with the problems with imbalanced datasets. The 10-fold cross-validation is used to assess the models. Accuracy and F1-score are used for model evaluation. F1-score is considered to be an important metric to measure the models for imbalanced datasets since the premise of churn management is to be able to identify customers who will churn. Experimental analysis indicates that AdaBoost performed the best in Dataset 1, with accuracy of 77.19% and F1-score of 63.11%. Random Forest performed the best in Dataset 2, with accuracy of 93.6% and F1-score of 77.20%. Random Forest performed the best in Dataset 3 in terms of accuracy, at 63.09%, while Multi-layer Perceptron performed the best in terms of F1-score, at 42.84%. After implementing churn prediction, Bayesian Logistic Regression is used to conduct the factor analysis and to figure out some important features for churn customer segmentation. Churn customer segmentation is then carried out using K-means clustering. Customers are segmented into different groups, which allows marketers and decision makers to adopt retention strategies more precisely.

The features of decentralization and tamper-proof enable blockchain to be an emerging technology for integrity protection of important data stored on it. Blockchains are also used to combine with cloud storage for access control and sharing of private data. To protect the confidentiality of the private data, attribute-based encryption (ABE) schemes that can provide one-to-many encryption are commonly used as the solutions. However, there are problems, such as inefficiency, key abuse, and inflexibility of access control policy, when adopting ABE solutions. This paper proposes an efficient traceable attribute-based encryption with dynamic access control (TABE-DAC) scheme based on blockchain for fine-grained sharing of encrypted private data on cloud. The proposed TABE-DAC scheme supports traceability for the accountability of malicious users who leak the private key. The proposed solution also realizes dynamic access control where data owners have the flexibility to update access control policy. We also prove the security of the proposed TABE-DAC scheme. Finally, through theoretical comparison and experimental analysis, we verify the efficiency of the proposed solution.

Policy-based chameleon hash (PCH) is one of the techniques used for rewriting transaction-level data stored in blockchains. This technique integrates the access policy of the attribute-based encryption (ABE) in the transactions and only allows users with attributes set satisfying the access policy to modify the transactions. However, some operations in the PCH-based rewritable blockchain solution require high computational cost which may impact the performance of user systems, especially on resource-constrained devices. To solve this problem, we propose an online/offline rewritable blockchain with auditable outsourced computation (OO-RB-AOC) scheme. We utilize the ring signature to ensure the credibility of multiple attribute authorities, and adopt the online/offline technique for generating the hash of the rewritable transaction. In addition, expensive computations (e.g., pairings) required for rewriting the transactions can be outsourced to the clouds. The users can rest assured that the computations from the clouds are correct with the audit mechanism of the proposed scheme. On the other hand, the proposed scheme offers a desirable feature for commercial application where the clouds can limit the number of outsourced requests according to the subscription of the users. We also prove the security of the proposed OO-RB-AOC scheme. Finally, we present a theoretical comparison and experimental analysis of the proposed scheme.

Recently, attribute-based keyword search (ABKS) schemes have been used to provide fine-grained search over encrypted data on eHealth cloud in the Internet of Things (IoT) platforms. As compared to conventional public key encryption with keyword search (PEKS) schemes, ABKS schemes provide more powerful and flexible search operations which allow encrypted data to be retrieved by multiple users that satisfy set of attributes. However, there are still some limitations and security issues on the existing ABKS schemes. Many of the existing ABKS schemes only support for the encryption of keyword and require a separate cryptographic primitive to encrypt the message. Also, most of the schemes cannot resist offline keyword guessing attacks by inside attackers (i.e., the honest-but-curious servers). A secure-channel is needed for most of the ABKS schemes to transmit the trapdoors between the server and receivers. To solve these problems, we propose a secure-channel free ciphertext-policy decryptable attribute-based keyword search (CP-DABKS) scheme. The proposed scheme allows the authorised user who satisfy the access structure to decrypt the ciphertext. Our scheme not only resists the insider keyword guessing attack, but also eliminates the secure channel for trapdoor transmission. We formally define and prove the security of the proposed CP-DABKS scheme. We also demonstrate its application on an eHealth cloud platform.