A large variety of fraud patterns combined with insufficient data on fraud makes insurance fraud detection a very challenging problem. Many algorithms are available today to classify fraudulent and genuine claims. To understand the various classification algorithms applied in fraud detection, I did a comparison using vehicle insurance claims data.
(more…)
Generating Malayalam Word Embeddings: A Case Study
Research shows that children primarily learn languages by observing patterns in the words they hear. Computer scientists are taking a similar approach to train computers to process human language.
NLP Libraries for Malayalam Sentence Tokenization: An Exploratory Study
Imagine that you are working on machine translation or a similar Natural Language Processing (NLP) problem. Can you process the corpus as a whole? No. You will have to break it into sentences first and then into words. This process of splitting input corpus into smaller subunits is known as tokenization. The resulting units are tokens. For instance, when paragraphs are split into sentences, each sentence is a token. This is a fairly straightforward process in English but not so in Malayalam (and some other Indic languages).
(more…)
Jetpack Compose—A Modern Declarative UI Toolkit for Android
In the dynamic realm of Android app development, it is not uncommon for new libraries, SDKs, and architectures to rise and fall and new features to get added or removed each year. Among the few things to survive the flux, the XML-based UI toolkit is relied on by developers to build user interfaces of all kinds. It is a bit of a tedious process: UI layouts are defined in an XML file, accessed and processed inside Kotlin files.
That normal is now slowly changing. Declarative and reactive UI toolkits and frameworks are shaking things up.
(more…)
Conversational AI Chatbot: Architecture Overview
Artificial Intelligence (AI) powers several business functions across industries today, its efficacy having been proven by many intelligent applications. Of the lot, chatbots are perhaps the most well-known. From healthcare to hospitality, retail to real estate, insurance to aviation, chatbots have become a ubiquitous and useful feature. But how are these chatbots created? Let’s take a look at the architecture of a conversational AI chatbot.
(more…)
A Friendly Intro to SOAP Web Services in Adobe Campaign
The option to communicate with external systems is a cool feature to have in any platform. In Adobe Campaign, daily updates from external systems are made via a CSV or TXT file. But what if we want to push real-time data to Adobe Campaign, and more specifically to the recipient table? Then we have to make use of SOAP web services.
(more…)
RPA—It’s Time to Take the Plunge
We all know the saying “Tough times never last, but tough people do.” We are going through one of the toughest times of our generation and the situation requires us to toughen up too. Businesses took a hit when the pandemic struck and had to improvise drastically to cope. Some had to scale down their operations while many others resumed with an almost entirely remote workforce. Only a small fraction of businesses are in a position to say they are highly prepared to deal with the impact according to Gartner’s recent Business Continuity Survey.
(more…)
Salesforce Notifications Simplified for Business Users
Salesforce business users may have been long waiting for a business solution for notifications. Whether it is Chatter notifications, Bell notifications, or the regular email alerts, every time a new scenario or change is needed, they must wait for developer or admin support to code in the change and configure the system. And tracking of notifications for a particular record is nothing less than a hunting job. The Notification App is an answer to these long-standing problems.
(more…)
Extracting Data from Common Crawl Dataset
In the field of natural language processing (NLP), data is king. The more data you have, the better your results. Most new research is freely accessible these days and, thanks to the cloud, there is unlimited computing power at our disposal. What keeps an NLP researcher from achieving state-of-the-art results despite this is the lack of good data.
(more…)
Making Logs Meaningful: The Role of Mapped Diagnostic Context
Logs in any computing program can be used to track its execution and how it is faring at the moment. Based on my experience here at QBurst, let me show you how to make meaningful logs in any backend application with proper contextual information. This post will specifically take a look at logging in Java and see how logs can be made meaningful, and then go on to introduce Mapped Diagnostic Context (MDC) logging.
(more…)