“Medha and I studied at the same university, though in different colleges. I always had a keen interest in Mathematics and Medha had a flair for programming. Medha told me that she was working on a project on the mathematical logic theory of sets, to develop a program which could solve any word problems based on the set theory, adaptive enough to still get the results even if the language of the question was completely changed or some junk data was provided. I was surprised to see that it actually worked! I think Medha is an extremely talented programmer and I hope she continues to amaze me, and the rest of the world with her skills. Rise high.”
About
Activity
-
We’re happy to introduce our team of Shubhaangi Mahajan, Yoram Mekking and Hector Bagley! Our summer startup project brings us to East Africa this…
We’re happy to introduce our team of Shubhaangi Mahajan, Yoram Mekking and Hector Bagley! Our summer startup project brings us to East Africa this…
Liked by Medha Sagar
-
✨FIVE Data Scientist roles with Sam's Club!🛒 Are you a Data Science whiz ready to make an impact? 🚀 We're hiring FIVE Data Scientist - Machine…
✨FIVE Data Scientist roles with Sam's Club!🛒 Are you a Data Science whiz ready to make an impact? 🚀 We're hiring FIVE Data Scientist - Machine…
Liked by Medha Sagar
-
📢 It is OK to Create Bad Content, But It is Not OK to Lose Your Identity for Clickbaits! 🚫🧩 Based on my content creation journey and engaging…
📢 It is OK to Create Bad Content, But It is Not OK to Lose Your Identity for Clickbaits! 🚫🧩 Based on my content creation journey and engaging…
Liked by Medha Sagar
Experience & Education
Publications
-
A Novel Approach to Solve Set-Theory Word Problems Automatically
IEEE
Abstract—Mathematical Word Problems (MWPs) are verbal
formulations of real-world scenarios representing an abstract
mathematical idea. They aid us in demonstrating the relevance
of mathematics in extrapolating everyday tasks. Set Theory is a
field of mathematics that is used to discern the nature of sets and
the relations between them. Set-theory operations are binary in
nature. They are used to depict the type of association between
two sets. In the current scenario, the…Abstract—Mathematical Word Problems (MWPs) are verbal
formulations of real-world scenarios representing an abstract
mathematical idea. They aid us in demonstrating the relevance
of mathematics in extrapolating everyday tasks. Set Theory is a
field of mathematics that is used to discern the nature of sets and
the relations between them. Set-theory operations are binary in
nature. They are used to depict the type of association between
two sets. In the current scenario, the difference in the levels
of abstraction of deriving regular expressions and interpreting
natural language poses a challenging task. In this paper, we
present a novel approach to solve set-theory based word problems
automatically using the semantics of the language. Our system
analyzes set-theory questions obtained from various sources of
informal text that are crowd sourced such as online forums, social
media and competitive examination portals and computes the
result by discerning the language of the problem. Our algorithm
mimics the paradigm through which humans attempt to solve
set-theory MWPs. We discretized our approach into two sub-
tasks, information extraction and problem solving, implementing
separate evaluation for each stage and subsequently ensuring that
the error propagation from one phase to the next is curbed and
efficiency for each stage can be individually determined. Our
system uses language semantics to identify the set entities in
a word problem, and subsequently maps these entities in an
expression that embodies the problem. In the problem solving
phase, we obtain the final result of the word problem by inferring
the relation that is to be determined and implementing the
corresponding set- theory function to compute the solution. We
corroborated our result for the two phases individually using
supervised learning. In the information extraction phase, our
system exhibited an accuracy of 83.5% and its performance in the
problem solving phase is 60%, -
Performance prediction and behavioral analysis of student programming ability
IEEE
Computer Programming as a process that embodies the creation of an executable computer program for a given computational problem by analyzing the task and developing an algorithm that computes the desired result. Due to its complex and diverse nature, programming requires a certain level of expertise in analysis of algorithms, data structures, mathematics, formal logic as well as related tasks such as testing and debugging. Due to increasing awareness of need for programming, there exists…
Computer Programming as a process that embodies the creation of an executable computer program for a given computational problem by analyzing the task and developing an algorithm that computes the desired result. Due to its complex and diverse nature, programming requires a certain level of expertise in analysis of algorithms, data structures, mathematics, formal logic as well as related tasks such as testing and debugging. Due to increasing awareness of need for programming, there exists numerous competitive programming websites where students can practice and solve problems. The aim of our work is to assess the performance of students on such platforms. This work shall not only help the learners to self-assess themselves, but it will also aid the educators to evaluate the progress of their students. To meet this objective, the data was collected from two different competitive programming environments, namely, HackerEarth-a globally accessible competitive programming website and our university's in-house programming portal, a university-based programming environment. We used supervised learning to predict the performance of students for both the datasets. The accuracy obtained for the HackerEarth dataset is 80%, while the accuracy for the University dataset was computed to be 91%. Apart from predicting the performance, rigorous analyses were done unearth hidden trends responsible for a learners programming acumen.
Courses
-
Applied Statistics and Experimental Design
DATA 557
-
Big Data for Machine Learning
CSE 547
-
Data Visualization
DATA 511
-
Database Management
CSE 514
-
Introduction to Probability and Statistics
DATA 556
-
Machine Learning
DATA 558
-
Macroeconomics
-
-
Microeconomics
-
Projects
-
Questia
Created a quiz based web application titled ”Questia”. The application provides campus placement questionnaires of leading IT companies in a quiz based format
-
Brainstorm-Collaborative Learning Portal
Attended workshop on Web- Based Application Development conducted by IGDTUW, and prepared a discussion portal titled “Brainstorm”, enabling students and teachers to hold discussions and post questions on various academic topics. It also evaluated students’ performance on the basis of their involvement in discussion forums. The portal won the “Best Project” award and now is live and used by IGDTUW (http://rk-labs.dyndns.org:8080/brainstorm/home.php)
Other creatorsSee project
Honors & Awards
-
Most Valuable Player
SAP Labs
Recognized as the 'Most Valuable Player' (in a team of 12)
-
Most Valuable Player
SAP Labs
Recognized as the 'Most Valuable Player' for my contributions to the project.
-
Spot Award
SAP Labs
Recognized as the best young talent in my team.
-
Best Project Award
Guru Gobind Singh Indraprastha University
Secured third position at ‘Inter-College Project Competition’ held at Indraprastha University. The competition is held annually showcasing the best final year projects from all colleges under GGSIPU
-
Best Project Award
Indira Gandhi Institute of Technology
Our project titled 'Brainstorm', a collaborative learning platform for teachers and students was selected for the best project award at college-level.
Languages
-
English
-
-
Hindi
-
Recommendations received
1 person has recommended Medha
Join now to viewMore activity by Medha
-
Lighting fast data exploration with SmartApps for the recent ML competition. With faster EDA, data scientists can focus on the next step of ML model…
Lighting fast data exploration with SmartApps for the recent ML competition. With faster EDA, data scientists can focus on the next step of ML model…
Liked by Medha Sagar
-
I’m excited to announce that I will be giving a technical talk at the Women in Data Science Conference in Seattle on April 25th at 1pm. The topic of…
I’m excited to announce that I will be giving a technical talk at the Women in Data Science Conference in Seattle on April 25th at 1pm. The topic of…
Liked by Medha Sagar
-
Hi connections, On my recent trip to India, the topic of discussion in every gathering was talking about recession, layoffs and managing finances…
Hi connections, On my recent trip to India, the topic of discussion in every gathering was talking about recession, layoffs and managing finances…
Liked by Medha Sagar
-
Hello LinkedIn family, I am delighted to inform you that I have accepted a position with Amazon as a Pathways Operations Manager Intern! I will…
Hello LinkedIn family, I am delighted to inform you that I have accepted a position with Amazon as a Pathways Operations Manager Intern! I will…
Liked by Medha Sagar
-
I am Delighted to share with you that I got 5th Position in the "Dalal Street Buzz" Quiz competition, conducted by the The Finance and Economics Club…
I am Delighted to share with you that I got 5th Position in the "Dalal Street Buzz" Quiz competition, conducted by the The Finance and Economics Club…
Liked by Medha Sagar
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More