Co-founder, QurioSkill. Helping individuals and organizations build and use AI Agents

github

Madhav Malhotra  • Peerlist

•	Studied Linear Optimization, using The Simplex Method and its various variations. •	Implemented Simplex, Revised Simplex, Two Phase and Dual Simplex based optimization methods in Python. •	Applied the simplex implementations, for optimizing the amount of stocks bought from Google, Amazon and IBM and evaluated its efficiency over a period of 2 weeks using Google Finance.

Linear Optimizer in Python, using The Simplex

•	Studied the service oriented architecture based software implementation models, using IBM’s white papers. •	Studied, in depth, the web service specification and communication models, specifically WSDL, XSD, JSON and REST. •	Implemented the IBM Websphere Message Broker architecture, for orchestrating the SOAP and/or JSON based web services to the end user web and mobile interfaces. •	Implemented network security mechanisms on IBM’s Data power, using SSL and Kerberos, for securing REST based web services, hosted on legacy Unix systems. •	Implemented queue based load balancing, for high traffic web services, using the IBM Websphere Message Queuing application.

Lloyds Banking System Web Service Architectur

•	Hypothesized different arrival and service rate distributions and queueing architectures, for web service requests in a banking system’s web architecture. •	Modeled the various systems using Omnet++, implementing the servers and queues. •	Simulated with various distributions and queuing times and performed a comparative performance analysis for figuring out the optimum distribution and queue architecture.

Omnet++ Simulation for a bank’s web service a

•	Developed a crowdsourced system for providing emergency Naloxone kit response service from good Samaritans to overdose events happening around the kit holders. •	Coordinated the rollout of the proof of concept mobile application, developed with React Native and Express (Node.js), with Aids Vancouver Island, a non-profit organization working in Victoria, British Columbia. •	Conceptualized and implemented an SMS based failover infrastructure, for the availability of the emergency service for phones with no data/internet availability.

Peer Alerting Lifeline: A Crowdsourced Emerge

•	Analyzed academic and technical literature on data mining for sentiment analysis on a variety of text corpus. •	Collected news article dataset, from GDELT online news services (http://www.gdeltproject.org/). •	Conducted a user survey, for categorizing the collected news items, as violent and non violent. •	Implemented Training using Python’s scikit-learn module, employing Decision Trees, Random Forests, Logistic Regression and SVM algorithms. The data was divided into training and test sets and td-idf vectorizer was used, to balance the usage of low frequency words in model training. •	Implemented parameter tuning on the implemented algorithms, using training, validation and test sets. •	The project resulted in a final model, having the accuracy of approximately 76 percent, in categorizing news articles on the basis of their violent and non violent content.