Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Match Maker: Text Analytics


Published on

Check out how Text Analytics plays match maker. Using appropriate techniques text analytics can go a long way in reducing the manual work in the social & legal areas such as contract management, structured document decomposition, sentiment analysis and even in news summation and dating and job portals. Techniques like natural language processing, word2vec, deep learning, TF-IDF are used to get the best output.

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Match Maker: Text Analytics

  1. 1. The Match Maker: Text Analytics at work October 5, 2017
  2. 2. Slide 2 About AlgoAnalytics Match Making: Problem Statement Text Analytics: Keyword Match Text Analytics: Use cases Other text analytics work Technologies
  3. 3. Slide 3 Aniruddha Pant CEO and Founder of AlgoAnalytics PhD, Control systems, University of California at Berkeley, USA 2001 • 20+ years in application of advanced mathematical techniques to academic and enterprise problems. • Experience in application of machine learning to various business problems. • Experience in financial markets trading; Indian as well as global markets. Highlights • Experience in cross-domain application of basic scientific process. • Research in areas ranging from biology to financial markets to military applications. • Close collaboration with premier educational institutes in India, USA & Europe. • Active involvement in startup ecosystem in India. Expertise • Vice President, Capital Metrics and Risk Solutions • Head of Analytics Competency Center, Persistent Systems • Scientist and Group Leader, Tata Consultancy Services Prior Experience • Work at the intersection of mathematics and other domains • Harness data to provide insight and solutions to our clients Analytics Consultancy • +30 data scientists with experience in mathematics and engineering • Team strengths include ability to deal with structured/ unstructured data, classical ML as well as deep learning using cutting edge methodologies Led by Aniruddha Pant • Develop advanced mathematical models or solutions for a wide range of industries: • Financial services, Retail, economics, healthcare, BFSI, telecom, … Expertise in Mathematics and Computer Science • Work closely with domain experts – either from the clients side or our own – to effectively model the problem to be solved Working with Domain Specialists About AlgoAnalytics
  4. 4. Slide 4 AlgoAnalytics - One Stop AI Shop Aniruddha Pant CEO and Founder of AlgoAnalytics •We use structured data to design our predictive analytics solutions like churn, recommender sys •We use techniques like clustering, Recurrent Neural Networks, Structured Data •We use text data analytics for designing solutions like sentiment analysis, news summarization and many more •We use techniques like natural languageprocessing, word2vec, deep learning, TF-IDF Text Data •Image data is used for predicting existence of particular pathology, image recognition and many others •We use techniques like deep learning – convolutional neural network, artificial neural networks and technologies like TensorFlow Image Data •We use sound data to design factory solutions like air leakage detection, identification of empty and loaded strokes from press data, engine- compressor fault detection •We use techniques like deep learning Sound Data BFSI •Dormancy Analysis •Recommender System •Credit/Collection Score Retail •Churn Analysis •Recommender System •Image Analytics Healthcare •Medical Image Diagnostics •Work flow optimization •Cash flow forecasting Socio-Legal •Contracts Management •Structured Document decomposition •Document similarity & keyword match in text analytics Internet of Things •Predictive in ovens •Air leakage detection •Engine/compressor fault detection Others •Algorithmic trading strategies •Risk sensing – network theory •Network failure model
  5. 5. Slide 5 Problem Statement: Match Making at Work Numerical Data: Gender, age, salary, locality, experience, education level Text Data: Industry, Role, Skill set, specialization How do we Match the best Job Seeker for a given Job Description? Features used to represent Job Description data and Job Seekers data are mentioned below : Job Description Data Job Seekers Data Campaign ID Jobseeker ID Industry Industry Function Function Gender Gender Minimum Age Age Minimum Salary Salary Skills Skills Locations Current Locality Minimum Experience Experience Education Education Specialization Specialization Profile status DataSet
  6. 6. Slide 6 The Techniques Employed For a given Job Description similarity with various Job seeker’s Profiles Text Processing Techniques: Word2Vec, tf-idf, Glove, are used for matching text data Vector Distance Calculation
  7. 7. Slide 7 The How? To find best matching search results fielded through text data or in conjunction with query and analysis of fielded numerical data Word2Vec: •Word2vec is a group of related models that are used to produce word embeddings. •These models are shallow, two-layer neural networks that are trained to reconstruct linguistic contexts of words. • Word2vec takes as its input a large corpus of text and produces a vector space, typically of several hundred dimensions, with each unique word in the corpus being assigned a corresponding vector in the space.
  8. 8. Slide 8 Text Analytics: Use Cases Finance: Search, compliance, money laundering Insurance: Sentiments of customer, claim adjuster notes Media: Social media and audio video content analytics Retail: based on customer feedback brand analytics Legal: Keyword Search, Contract Management Healthcare: Medical records Social Spheres: Caption generation to help the visually-disabled, Marriage Matchmaking, dating services Text Analytics can be used over a variety of domains and solve many manual oriented problems
  9. 9. Slide 9 Twitter Analytics - Identify, process and group together relevant tweets using machine learning methods News Analytics - Access, identify and analyze relevant news article given a topic - News summarization App Development - Download, analyze twitter feeds of stocks to get sentiment and topic detection Multi-language Sentiment Analysis - Model can be used to get similar words. - Trained model can learn proximity of words Topic Summary, Concept Detection - Keyword extraction -summary extraction - Topic detection -Words Importance
  10. 10. Slide 10 Technology:
  11. 11. Interested in knowing more? Contact us: Website: October 5, 2017