Koushik Modayur Chandramouleeswaran has extensive experience developing software using various programming languages and technologies. He is pursuing a Master of Science in Computer Science from The University of Texas at Arlington with a GPA of 3.62/4.0 and holds a Bachelor of Technology in IT from Bharath University in India with a GPA of 8.44/10. He has worked as an Associate and Programmer Analyst at Cognizant Technology Solutions, developing tools and reports to help clients save over $120k. Koushik has strong skills in Python, Java, R, databases, big data technologies and machine learning. He has completed several projects applying techniques like decision
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.aiSri Ambati
This talk was given at H2O World 2018 NYC and can be viewed here: https://youtu.be/vUqC8UPw9SU
Description:
The good news is building fair, accountable, and transparent machine learning systems is possible. The bad news is it’s harder than many blogs and software package docs would have you believe. The truth is nearly all interpretable machine learning techniques generate approximate explanations, that the fields of eXplainable AI (XAI) and Fairness, Accountability, and Transparency in Machine Learning (FAT/ML) are very new, and that few best practices have been widely agreed upon. This combination can lead to some ugly outcomes! This talk aims to make your interpretable machine learning project a success by describing fundamental technical challenges you will face in building an interpretable machine learning system, defining the real-world value proposition of approximate explanations for exact models, and then outlining the following viable techniques for debugging, explaining, and testing machine learning models: *Model visualizations including decision tree surrogate models, individual conditional expectation (ICE) plots, partial dependence plots, and residual analysis. *Reason code generation techniques like LIME, Shapley explanations, and Treeinterpreter. *Sensitivity Analysis. Plenty of guidance on when, and when not, to use these techniques will also be shared, and the talk will conclude by providing guidelines for testing generated explanations themselves for accuracy and stability. Open source examples (with lots of comments and helpful hints) for building interpretable machine learning systems are available to accompany the talk at: https://github.com/jphall663/interpretable_machine_learning_with_python Bio: Patrick Hall is senior director for data science products at H2O.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2O.ai, Patrick held global customer facing roles and research and development roles at SAS Institute.
Speaker's Bio:
Patrick Hall is a senior director for data science products at H2o.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2o.ai, Patrick held global customer facing roles and R & D research roles at SAS Institute. He holds multiple patents in automated market segmentation using clustering and deep neural networks. Patrick was the 11th person worldwide to become a Cloudera certified data scientist. He studied computational chemistry at the University of Illinois before graduating from the Institute for Advanced Analytics at North Carolina State University.
Practical Tips for Interpreting Machine Learning Models - Patrick Hall, H2O.aiSri Ambati
This talk was given at H2O World 2018 NYC and can be viewed here: https://youtu.be/vUqC8UPw9SU
Description:
The good news is building fair, accountable, and transparent machine learning systems is possible. The bad news is it’s harder than many blogs and software package docs would have you believe. The truth is nearly all interpretable machine learning techniques generate approximate explanations, that the fields of eXplainable AI (XAI) and Fairness, Accountability, and Transparency in Machine Learning (FAT/ML) are very new, and that few best practices have been widely agreed upon. This combination can lead to some ugly outcomes! This talk aims to make your interpretable machine learning project a success by describing fundamental technical challenges you will face in building an interpretable machine learning system, defining the real-world value proposition of approximate explanations for exact models, and then outlining the following viable techniques for debugging, explaining, and testing machine learning models: *Model visualizations including decision tree surrogate models, individual conditional expectation (ICE) plots, partial dependence plots, and residual analysis. *Reason code generation techniques like LIME, Shapley explanations, and Treeinterpreter. *Sensitivity Analysis. Plenty of guidance on when, and when not, to use these techniques will also be shared, and the talk will conclude by providing guidelines for testing generated explanations themselves for accuracy and stability. Open source examples (with lots of comments and helpful hints) for building interpretable machine learning systems are available to accompany the talk at: https://github.com/jphall663/interpretable_machine_learning_with_python Bio: Patrick Hall is senior director for data science products at H2O.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2O.ai, Patrick held global customer facing roles and research and development roles at SAS Institute.
Speaker's Bio:
Patrick Hall is a senior director for data science products at H2o.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2o.ai, Patrick held global customer facing roles and R & D research roles at SAS Institute. He holds multiple patents in automated market segmentation using clustering and deep neural networks. Patrick was the 11th person worldwide to become a Cloudera certified data scientist. He studied computational chemistry at the University of Illinois before graduating from the Institute for Advanced Analytics at North Carolina State University.
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...Sri Ambati
This talk was given at H2O World 2018 NYC and can be viewed here: https://youtu.be/xc3j20Om3UM
Description:
Data science is indeed one of the sexy jobs of the 21st century. But it is also a lot of hard work. And the hard work is seldom about the math or the algorithms. It is about building relevant machine learning products for the real world. We will go over some of the must-haves as you take your machine learning model out of the sandbox and make it work in the big, bad world outside.
Speaker's Bio:
Krish Swamy is an experienced professional with deep skills in applying analytics and BigData capabilities to challenging business problems and driving customer insights. Krish's analytic experience includes marketing and pricing, credit risk, digital analytics and most recently, big data analytics and data transformation. His key experiences lie in banking and financial services, the digital customer experience domain, with a background in management consulting. Other key skills include influencing organizational change towards a data and analytics driven culture, and building teams of analysts, statisticians and data scientists.
Predicting the Future with Azure Machine LearningPaul Prae
In this talk, I focus on supervised learning, a machine learning technique for performing predictive analytics. After introducing some vocabulary, I discuss the relationship between predictive analytics and machine learning. Next, I describe how you could use a classifier, such as a decision tree, to predict which passengers survived the sinking of the Titanic. Once the machine learning process is clear, I then talk about how Azure Machine Learning is an end-to-end data science solution. Finally, I demo an experiment that predicts the outcomes of patients who went through substance abuse treatment.
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...Sri Ambati
This talk was given at H2O World 2018 NYC and can be viewed here: https://youtu.be/xc3j20Om3UM
Description:
Data science is indeed one of the sexy jobs of the 21st century. But it is also a lot of hard work. And the hard work is seldom about the math or the algorithms. It is about building relevant machine learning products for the real world. We will go over some of the must-haves as you take your machine learning model out of the sandbox and make it work in the big, bad world outside.
Speaker's Bio:
Krish Swamy is an experienced professional with deep skills in applying analytics and BigData capabilities to challenging business problems and driving customer insights. Krish's analytic experience includes marketing and pricing, credit risk, digital analytics and most recently, big data analytics and data transformation. His key experiences lie in banking and financial services, the digital customer experience domain, with a background in management consulting. Other key skills include influencing organizational change towards a data and analytics driven culture, and building teams of analysts, statisticians and data scientists.
Predicting the Future with Azure Machine LearningPaul Prae
In this talk, I focus on supervised learning, a machine learning technique for performing predictive analytics. After introducing some vocabulary, I discuss the relationship between predictive analytics and machine learning. Next, I describe how you could use a classifier, such as a decision tree, to predict which passengers survived the sinking of the Titanic. Once the machine learning process is clear, I then talk about how Azure Machine Learning is an end-to-end data science solution. Finally, I demo an experiment that predicts the outcomes of patients who went through substance abuse treatment.
1. Koushik Modayur Chandramouleeswaran
607, Summit Avenue APT 396 ARLINGTON TX 76013 (682)-230-1906 koushik394@gmail.com
EDUCATION
MASTER OF SCIENCE (COMPUTER SCIENCE) GPA 3.62/4.0 Graduating: May'16
The University of Texas at Arlington, Texas, USA.
BACHELOR OF TECHNOLOGY (I.T) GPA 8.44/10 Graduated: May'09
Bharath University, Chennai, India.
RELEVANT COURSE WORK
Distributed Systems Cloud Computing Database Models and Implementations
Data Mining Machine Learning Enterprise Software Development
Design and Analysis of Algorithms Database System
WORK EXPERIENCE
Cognizant Technology Solutions, Chennai, India
Associate, Projects June'13-July'14(13months)
Developed a prediction tool to predict the overall runtime of the batch processing. This prediction ensured that appropriate
measures could be taken for completing the process within the SLA in case of delays.
Developed software modules to automate payee addition functionality thereby reducing the cost by $20k.
Programmer Analyst March'10-June'13 (39 months)
Worked as a developer in the Business Intelligence team and developed reports for a leading financial institution.
Developed business critical reports which were used to take strategic business decisions resulting in a savings of $100K.
CERTIFICATIONS
EDX
Introduction to Big Data with Apache Spark
Scalable Machine Learning
Big Data X Series
Coursera
Data-science Specialization
o Statistical Inference
o Regression Models
TECHNICAL SKILLS
Programming Languages/Scripting: Python, Java, R, Open Edge Progress 4 GL
Databases: MySQL, Oracle, MS SqlServer, Amazon Dynamo DB, MongoDB
Big Data/Cloud: Hadoop, Apache Spark, Hive, Pig, Cassandra, Amazon Web Services (AWS), Google AppEngine
Web Development: Html, Css, JavaScript, J2EE, Php, Flask
Libraries/packages: Numpy, Scipy, sci-kitlearn, Pandas, Weka
PROJECTS
Decision Tree and Bagging: Built a Decision Tree based classifier in python [Accuracy: 72%].Bagging was implemented by building
training dataset using the re-sampling with repeats [Improved Accuracy: 84%].
KNN Classifier: Built a K-nearest neighbor classifier using python. The task of the classifier was to predict the gender of a person given the
other attributes [Accuracy: 85%].
Search Engine: - Built a search engine for retrieving medical prescriptions of patients from MongoDB. Bootstrap was used to design the
user interface on the flask framework along with Jinja2.
Movie Recommendation Using Apache Spark: Collaborative filtering method was used to perform movie rating predictions, a prediction
model was built using the Alternating Least Squares implementation in MLLIB in Spark and cross-validated.
Image classification using Artificial Neural Network: Developed a neural network based image classifier in Octave using back
propagation and gradient descent [Model Accuracy: 80%].
Data clustering visualization in D3.js: Developed a responsive web application using D3.js hosted in AWS Elastic Beanstalk to upload
data, choose attributes to cluster, cluster using Weka and visualize the clustered scatterplots.
Exploratory Data Analysis Using Hadoop and R: Developed a Map-Reduce program to analyze NCDC data to perform predictive time-
series analysis of different climatic attributes and visualize the results in R.
GitHub: - https://github.com/Koushikmc/ LinkedIn: - www.linkedin.com/pub/koushik-chandramouleeswaran/14/958/3ab/