Analytics and AI for Industry - Specific Applications
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 5
-
ItemDeep Learning for Improved Agricultural Risk Management( 2019-01-08)
-
ItemFraudMemory: Explainable Memory-Enhanced Sequential Neural Networks for Financial Fraud Detection( 2019-01-08)The rapid development of electronic financial services brings significant convenience to our daily life. However, it also offers criminals the opportunity to exploit financial systems to do fraudulent transactions. Previous studies on fraud detection only deal with single type transactions and cannot adapt well to evolving environment in reality. In addition, their black box models pay less attention on the interpretability of fraud detection results. Here we propose a novel fraud detection algorithm called FraudMemory. It adopts state-of-art feature representation methods to better depict users and logs with multiple types in financial systems. Our model innovatively uses sequential model to capture the sequential patterns of each transaction and leverages memory networks to improve both the performance and interpretability. Also, with the incorporation of memory components, FraudMemory possesses high adaptability to the existence of concept drift. The empirical study proves that our model is a potential tool for financial fraud detection.
-
ItemBusiness Analytics for Sales Pipeline Management in the Software Industry: A Machine Learning Perspective( 2019-01-08)This study proposes a model designed to help sales representatives in the software industry to manage the complex sales pipeline. By integrating business analytics in the form of machine learning into lead and opportunity management, data-driven qualification support reduces the high degree of arbitrariness caused by professional expertise and experiences. Through the case study of a software provider, we developed an artifact consisting of three models to map the end-to-end sales pipeline process using real business data from the company’s CRM system. The results show a superiority of the CatBoost and Random Forest algorithm over other supervised classifiers such as Support Vector Machine, XGBoost, and Decision Tree as the baseline. The study also reveals that the probability of either winning or losing a sales deal in the early lead stage is more difficult to predict than analyzing the lead and opportunity phases separately. Furthermore, an explanation functionality for individual predictions is provided.
-
ItemHolistic System-Analytics as an Alternative to Isolated Sensor Technology: A Condition Monitoring Use Case( 2019-01-08)Sensor technology has become increasingly important (e.g., Industry 4.0, IoT). Large numbers of machines and products are equipped with sensors to constantly monitor their condition. Usually, the condition of an entire system is inferred through sensors in parts of the system by means of a multiplicity of methods and techniques. This so-called condition monitoring can thus reduce the downtime costs of a machine through improved maintenance scheduling. However, for small components as well as relatively inexpensive or immutable parts of a machine, sometimes it is not possible or uneconomical to embed sensors. We propose a system-oriented concept of how to monitor individual components of a complex technical system without including additional sensor technology. By using already existing sensors from the environment combined with machine learning techniques, we are able to infer the condition of a system component, without actually observing it. In consequence condition monitoring or additional services based on the component's behavior can be developed without overcoming the challenges of sensor implementation.
-
Item