Surya Putchala

Amongst the recent developments in the Computing, Mobile Technologies are enabling making information and data available to the users without location or temporal constraints. Various business and personal productivity applications are being increasingly deployed on Mobile Platforms. As mobile devices proliferate, there will be an increased emphasis on serving the needs of the mobile user in diverse contexts and environments, which are being called Data products. Mobility also impose… Show more

Amongst the recent developments in the Computing, Mobile Technologies are enabling making information and data available to the users without location or temporal constraints. Various business and personal productivity applications are being increasingly deployed on Mobile Platforms. As mobile devices proliferate, there will be an increased emphasis on serving the needs of the mobile user in diverse contexts and environments, which are being called Data products. Mobility also impose significant management challenges for IT organizations as they lose control of user endpoint devices. There is a need for a unified mobile deployment platform or mBaaS (i.e Mobile Backend as a Service) that can integrate various data products and serve new features to all the users of an enterprise. This mBaaS when deployed on the cloud can scale elastically depending on the workload characteristics. Show less

To build the Ranking and Scoring Algorithm for Mobile App Recommendation system, there are different parameters have to be taken into the consideration. Aim of this Project is for informing the sentiment of reviews and comments of Mobile Apps. Our new deep learning model is to obtain a suitable representation of text structure and thus make it possible to process texts based on their content of whole sentences based on the sentence structure, meaning of words, phrases, and subsequently also… Show more

To build the Ranking and Scoring Algorithm for Mobile App Recommendation system, there are different parameters have to be taken into the consideration. Aim of this Project is for informing the sentiment of reviews and comments of Mobile Apps. Our new deep learning model is to obtain a suitable representation of text structure and thus make it possible to process texts based on their content of whole sentences based on the sentence structure, meaning of words, phrases, and subsequently also their purpose and consequence, by giving positive points for positive words and negative points for negative words and compute the sentiment based on how words compose the meaning of longer phrases. To implement this project we are using NLP Services such as Tokenization,Tagging parts of speech,Text Summarization,Text Classification and Text Processing. Show less

An App store is a digital distribution platform for mobile applications. Every day hundreds of new mobile apps are developed and made available on the App stores. Since, there may be multiple apps stores, many new/old apps will not be visible for the users owing to the traditional listing of Apps based on the total downloads, ratings, popularity etc., Thus, there is a need to enhance the visibility of these applications based on features such as functionality, trending, reviews, category… Show more

An App store is a digital distribution platform for mobile applications. Every day hundreds of new mobile apps are developed and made available on the App stores. Since, there may be multiple apps stores, many new/old apps will not be visible for the users owing to the traditional listing of Apps based on the total downloads, ratings, popularity etc., Thus, there is a need to enhance the visibility of these applications based on features such as functionality, trending, reviews, category, search characteristics of all users etc.,The aim of this project is to not only recommend app on its characteristics but also recommend them on the basis user characteristics such as his current app portfolio, interests, and propensity for a category of apps. This project will be implemented in two phases - the first phase is “Ranking and Scoring” of the mobile applications. The second phase is to develop a recommender system on the basis of user characteristics, activities and preferences. Show less

Currently, developing an algorithm to detect spurious resumes, veracity of claims of credentials int he resume's uploaded by job seekers for a Job Portal. The goal of the project is to get the right job seeker to the right company thus improving the hiring cycle, misfits for a job and the costs of hiring the right candidate. It is beneficial both to the job seeker and the employer. A text Analytics, graphs, recommender methods are being deployed to address this challenging project

The businesses are increasing moving their marketing activities from traditional marketing channels to digital marketing channels. This new shift gives an opportunity for the marketing teams to personalize and customize services to any user in question. The Ads are transmitted to match the needs of a specific customer base. Ad Server platforms makes this possible. The Ad Server platforms has access to data related to Users, Stores, User Ad Clicks, Internet Publishers, Advertisers, Campaigns… Show more

The businesses are increasing moving their marketing activities from traditional marketing channels to digital marketing channels. This new shift gives an opportunity for the marketing teams to personalize and customize services to any user in question. The Ads are transmitted to match the needs of a specific customer base. Ad Server platforms makes this possible. The Ad Server platforms has access to data related to Users, Stores, User Ad Clicks, Internet Publishers, Advertisers, Campaigns etc., The purpose of this project however is to develop and deploying core learning algorithms for determining Home locations for the users based on the Ad server Clicks and Matching Store locations/Ads for the Users. These Algorithms for the Ad Servers optimizes marketing campaigns and website behavior to improve customer responses and conversions.

This Data is not available as an open data, hence there is a need for synthesizing the data. This project also creates the necessary transaction data using Monte Carlo Simulation. Show less

This recommender system is developed for a Job portal. Matched the jobs to the job seekers based on skill sets, location, psychometric profile, qualifications and a host of other variables. The data set sizes exceeded 5 TB, We have set up a 6 node Hadoop Cluster. We have used, Solr, Nutch for the indexing and searching. Similarity algorithms for clustering. We are continuously improving the algorithms by including various authenticity factors.

In a social network, common characteristics of a set of nodes (location, interests, occupation, etc.,) can be called a community. For law enforcement, a network drawn on the basis of call detail records (CDR) provide a wealth of information that can help to identify suspects, in that they can reveal details as to an individual's relationships with associates, communication, behavior patterns, location data can establish a community of suspects perpetrating a crime. Since, relational databases… Show more

In a social network, common characteristics of a set of nodes (location, interests, occupation, etc.,) can be called a community. For law enforcement, a network drawn on the basis of call detail records (CDR) provide a wealth of information that can help to identify suspects, in that they can reveal details as to an individual's relationships with associates, communication, behavior patterns, location data can establish a community of suspects perpetrating a crime. Since, relational databases cannot scale when the hierarchical queries, direct querying is infeasible to detect "network" patterns. The traditional Community detection is essentially clustering (distance or similarity measures). Network data tends to be "discrete", leading to algorithms using the graph property directly (cliques and centrality) in order to detect communities.

The objective of this project is to identify a terrorist network whose community property being closely knit sizes between 3 to 10, and uncovering calling patterns as identified by criminal psychologists. There are about 2 Billion Call Data Records (CDR) and 200 Million unique contacts in the network. The approach is to initially eliminate the non-suspects (Big data Processing) and later identifying the suspects (Machine learning and Statistical analysis).

We have used 10 Node Hadoop Cluster to process 25 Terabytes of Data using MapReduce and HBase. The Algorithmic treatment involved Community detection and Collaborative filtering. We have used eclectic methods of Graph traversals and visualization. Show less