Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Filters

20192

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Analysis Based

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    Potential upselling customer prediction through user behavior analysis based on CDR data
    (IEEE, 2019-12-18) Manchanayake, S. M. A. M; Samarasinghe, D. P; Perera, L. P. J; Bandara, H. M. M. T; Kumaradasa, K. C; Premadasa, N; Samarasinghe, P
    Upselling is a valuable technique for increasing the profit margin of any service providing business domain. It plays a vital role in growth of a company. Among those companies, telecommunication industry is a prominent industry where upselling is highly influenced on churn reduction and stabilizing the customer base. As this increases the satisfaction of customers through adding products and services it is very effective in a marketing perspective. In a typical 4G LTE package marketing, customer will be offered to select a fixed package out of a set of pre-defined packages. The decision of selecting a suitable package by customer will be mainly an instinct driven decision due to lack of previous experience of using an LTE package. This will result in selecting an unsuitable package, which will lead to over usage of data. As a result, it will cause customer dissatisfaction and loss of potential income for the company. Therefore, it is essential for a telecommunication company to identify the customers who have the potential to upgrade their packages based on customer usage. In this research, potential package upgrades are predicted for LTE broadband users through a supervised learning method using different classification models. One of the key factors on obtaining a high accuracy model for classifying customers is to address the class imbalance problem that is present in the telecommunication data. The ratio between potential package upgrades and normal customers is highly skewed towards normal customers. This is addressed using SMOTE which is an oversampling method that creates synthetic samples using existing data points. Potential customers identified by a classification model trained by a dataset consist of usage behavior. The prediction results will be published to a dashboard that can be consumed by decision makers.
  • Thumbnail Image
    PublicationEmbargo
    Air Visio: Air Quality Monitoring and Analysis Based Predictive System
    (IEEE, 2019-12-05) Dissanayaka, A. D; Taniya, W. A. D; De Silva, B. P. A. N; Senarathne, A. N; Wijesiri, M. P. M; Kahandawaarachchi, K. A. D. C. P
    Sri Lanka is facing a serious air pollution problem that severely impacts the daily life of every Sri Lankan. The main source of ambient air pollution in Sri Lanka is vehicular emissions. A methodology to monitor the air quality in real-time with an overall coverage of Sri Lanka, and automatically process these huge data to identify air quality levels in a specific area is now becoming a timely research topic. An air quality monitoring and analysis based predictive system is proposed to monitor the ambient air quality, provides the best route with minimum polluted air, maps the heatmaps to identify the current air quality of an area easily and predict the future air quality of each area. The prototype was implemented by hierarchically deploying two different gas sensors, an Arduino Uno board and a wifi module, to implement in open spaces between smart buildings, and transfers the sensor data back to the information processing center by using IoT technology for real-time display. The information processing center stores real-time information which is collected from the sensors to the database. By reading sensor data stored in the database, the front-end system draws real-time, accurate air quality levels included maps and predicts the less polluted routes and the air quality level over an area. Further, an energy harvesting system is also presented for the power consumption of the device. A route is suggested in an accuracy of 70% from this system. The final product provides a low cost, highly portable and easily maintainable system for the users.