The healthcare sector deals with large volumes of electronic data related to patient services. This article describes two novel applications that leverage big data to detect fraud, abuse, waste, and errors in health insurance claims, thus reducing recurrent losses and facilitating enhanced patient care. The results indicate that claim anomalies detected using these applications help
Fei Wang, Sanjay Chawla, and Wei Liu. “Tikhonov or lasso regularization: Which is better and when. In Tools with Artificial Intelligence” (ICTAI), 2013 IEEE 25th International Conference on, pages 795–802. IEEE, 2013. It is well known that supervised learning problems with ℓ1 (Lasso) and ℓ2 (Tikhonov or Ridge) regularizers will result in very different solutions. For example,
Sanjay Chawla, Federico Girosi, Fei Wang “Data Science and the Policy Completion Problem” The link between policy analysis and data science is more delicate than it may appear. A new policy, by definition, will change the underlying data generating model, rendering classification or supervised learning inapplicable. Perhaps eliciting causal relations from observational data is the
Governments as well as health and accident compensation insurers are grappling to improve health outcomes while keeping spiraling costs under control. These seemingly irreconcilable goals require a careful balance of policy to help stem the tide of ever increasing costs in the health industry. Dr Uma Srinivasan CMC Insurance Solutions CMC Lead Scientist Keywords: Health insurance,
A study by CMCRC researchers presents a fresh look at extracting apposition from large collections of news, web and broadcast text in order to turn unstructured news stories into “computable data”. News is about interactions between entities ‐ people, places and organisations ‐ and understanding stories requires interpreting the entities in them and their attributes.
Researcher discovers that a combination of adversarial learning and sparse modelling techniques improves the performance of an email/spam classifier. Fei Wang CMCRC PhD candidate U. of Sydney Prof Sanjay Chawla CMCRC Research Leader U. of Sydney Classifiers are widely used in many computer-based applications to the bene- fit of virtually all computer users. An
Study looks at combining text data and financial quantitative data to produce a model for predicting a stocks daily return. Tony Zhao Zhao is a PhD student at Macquarie University. He has worked on a wide range of topics including embedded systems, digital signal processing, machine learning, large-scale data processing and natural language processing but
Researchers produce a new framework, StreamEB, which could revolutionise the visual analysis of data and graph streams. Dr Quan Nguyen CMCRC PhD graduate U. of Sydney Prof Peter Eades CMCRC Research Leader U. of Sydney High velocity data streams such as trading data have become ubiquitous since the 1990s and graph streaming is becoming
The development of a sophisticated and workable Named Entity Linking (NEL) system will enable the creation of new software allowing users to find vast amounts of news information about a named entity at the touch of a button. Will Radford CMCRC PhD candidate U. of Sydney A/Professor James Curran CMCRC Research Associate U. of Sydney
Governments as well as health and accident compensation insurers are grappling to improve health outcomes while keeping spiralling costs under control. These seemingly irreconcilable goals require a careful balance of policy to help stem the tide of ever increasing costs in the health industry. Dr Uma Srinivasan CMC Insurance Solutions CMC Lead Scientist Keywords: Health insurance,