Hi There, I'm Pranshu Tiwari

Data Science and Strategy

 I completed my MS in Mathematics: Operations Research from Northeastern University, I am Former IBM Senior Inventor and working as Managing Consultant -Data Science and Strategy. My key interest are using AI /Data Science to improve AI/Architecture / Design and Solve Complex Industiral Problems. I also did MS in Data Science(1 subject left) and have done MBA in 2005 from Ponts Tech Paris.

Pranshu Tiwari

About Me

Address

Address - 836 Willard Street | Quincy, MA 0216

Email

pranshu.ti12@gmail.com

Phone Number

(612) 716-3694

LinkedIn

linkedin.com/in/pranshu-tiwari-18973a10/

Pranshu Tiwari has 15 years of experience in Strategic Consulting and is a Data Science /AI Professional. He has MS – Operations Research from Northeastern University-Boston and is a project away from completing his third master’s in data science from University of Wisconsin. He has done MBA from Paris Tech -India and B.E in Electrical Engineering from Madras University. His data science Projects include FOAK Drug Recommendation System, Detect Cancer from CT scans of Brain for academia as well as Text Processing based Supervised Machine Learning. He has leadership experience of 10+ years in field of Consulting & Program Delivery and 4 Granted Patents with 14 Filed Patents in IBM. With Depth and Breadth of deep educational and industrial experience across multiple geographies, he is poised to take challenging opportunities to help companies navigate through various Industrial imperatives of AI/Digital and Cloud. He is avid Tennis player and competes in USTA 4.0 and regional tournaments. He also has interest exploring various Meditation techniques personal and spiritual growth

 

Tennis

Pranshu is an active tennis player. He has a serve and volley game and has a single handed backhand. He plays singles /doubles twice a week. He competes at USTA, Boston Tennis League. You can refer his latest tennis record on the following link:

Link 1

Link 2

 

Education

2002
2005
August 2021
2021

Highlights - Digital & AI

Artificial Intelligence

  • Developed FOAK Persona based Drug Recommendation System based on Content Filtering & Comparison of Predicted Rating based on Different Pre-Processing Architectures
  • 90% performance in Brain Cancer Detection using CNN Filters
  • 80% Accuracy in Predicting Stock Price Direction based on Different Pre-processing Architectures and RNN models
  • Created First of a Kind IBM patented AI based Dev Ops Branching Technique which minimizes build prediction failures
  • Developed FOAK IBM Patented Electrical Device Degradation System
Digital / Technology Strategy
 
  • Developed FOAK MDM based Revenue Assurance System for Client in India
  • Won Mega Deal for Revenue Assurance Deal in Mexico
  • Created a Data Quality Roadmap for Utility in UK to improve its data quality
  • Performance Test Strategy for Leading Utility in US
  • Led a team for Successful Digital Re-invention Program to compare and Contrast for advanced Digital Programs
  • Mobile Commerce Strategy for Leading Telco in Malaysia
  • Enterprise Data Quality Roadmap for a Utility in UK
  • Customer Transformation Roadmap for Improved Experience in US
  • Unique ID Report Assessment to Govt of India

Key Skills

Artificial Intelligence

 

  • Bayesian Theory & Maximum Likelihood
  • Unsupervised Machine Learning
  • Gradient Descent & Supervised ML
  • Matrix Vector Decomposition
  • Artificial Neural Network
  • Convolution Neural Network
  • Fourier & Gabor Transformation
  • Natural Language Processing
  • Linear & Integer Programming
  • Markov Chain & Genetic Algorithm
  • Tensor Flow, Kera’s, NumPy, Sklearn & R Libraries
Digital / Technology Strategy

 

  • Client Experience Management
  • Application Rationalization
  • Transformation Roadmap
  • Cloud Migration Assessment
  • Information Strategy Roadmap
  • Business Analysis
  • Mobile Commerce Strategy
  • Project Management-Agile & SDP
  • Master Data Management Strategy
  • RFP & Vendor Selection

PORTFOLIO - PRANSHU TIWARI

download (1) (1)

Insurance Risk Rating based on Maximum Lkelihood Estimation

Tweeter analysis

Tweeter Analysis to cmpare Branding of 2 Sports Companies

How health care

Insights from Patient Data for Disease Predction & Dynamic pricing 

Markov

Markov Based Models for Time Series Predicion of Energy States

Persona based

Persona based Drug Recommendation Systm based on Machine Learning

newspapers

RNN and  Likelihood based Models for Stock Price Prediction based on Daily News

PROFESSIONAL EXPERIENCE

2005 - 2006 Research Analyst
2006 - 2008 Associate Consultant
2009 - 2011 Lead Consultant
2011 - 2014 Advisory Consultant
2014 - 2017 Senior Advisory Consultant
2017 - Till Date Managing Consultant

Patents and Awards

  • 3 Plateau Award from IBM CEO 2017, 2020

 

  • Honored IBM Senior Inventor in 2017

 

  • Manager Choice Award 2014, 2017

 

  • Treasured Wild Ducks 2016

 

  • Shared Expertise 2016

 

  • Top Contributor 2015, 2016,2017

PATENTS BY INVENTOR PRANSHU TIWARI

Pranshu Tiwari has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

Patent number: 11093229

Abstract: A failure rate model modeling a failure rate of a training functionality deployment in a training set of functionality deployments is constructed. The failure rate model is configured to receive functionality deployment data and output a corresponding failure rate prediction. Using the failure rate model, a set of functionality deployment failure rates is predicted, a functionality deployment failure rate in the set of functionality deployment failure rates corresponding to an upcoming functionality deployment. Using the set of functionality deployment failure rates, a deployment sequence of the set of upcoming functionality deployments is constructed to minimize a predicted overall failure rate of the set of upcoming functionality deployments. The deployment of each functionality deployment in the set of upcoming functionality deployments is caused, the deployment comprising activating the upcoming functionality program code according to the deployment sequence.

 

Type: Grant

Filed: January 22, 2020

Date of Patent: August 17, 2021

Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventors: Pranshu Tiwari, Harish Bharti, Naveen Narayanaswamy, Ram Prasad Reddy Munagala

Publication number: 20210241392

Abstract: Methods and systems for metrics for energy saving and response behavior are disclosed. A method includes: receiving, by a computing device, for each of a plurality of energy users, consumption time series data from a smart meter of the energy user; determining, by the computing device, for each of the plurality of energy users, demographic data of the energy user; clustering, by the computing device, the energy users based on the consumption time series data and the demographic data; identifying, by the computing device, a plurality of groups of energy users based upon the clustering; and determining, by the computing device, an energy saving program to associate with each of the plurality of groups.

 

Type: Application

Filed: February 5, 2020

Publication date: August 5, 2021

Inventors: Pranshu TIWARI, Harish BHARTI, Saurabh TREHAN, Anshul CHETAL

Patent number: 10935970
Abstract: A method collects from at least one power measuring device of an environment power consumption data indicating active power consumption during a timeframe by an electrical device in the environment. The method also collects operating parameter data indicating at least one operating parameter under which the electrical device operates during at least a portion of the timeframe. The method performs, based on observing an increase in power consumption of the electrical device during the timeframe, assessing extents of contribution by potential contributing factors to the increase in power consumption, the potential contributing factors including time-based degradation of the electrical device and the at least one operating parameter. The method outputs, based on the assessing, an indication of an extent of contribution of degradation of the electrical device to the increase in power consumption.
 
Type: Grant
Filed: October 10, 2019
Date of Patent: March 2, 2021
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors: Harish Bharti, Abhay K. Patra, Pranshu Tiwari, Saurabh Trehan
Patent number: 10558206
Abstract: A method collects from at least one power measuring device of an environment power consumption data indicating active power consumption during a timeframe by an electrical device in the environment. The method also collects operating parameter data indicating at least one operating parameter under which the electrical device operates during at least a portion of the timeframe. The method performs, based on observing an increase in power consumption of the electrical device during the timeframe, assessing extents of contribution by potential contributing factors to the increase in power consumption, the potential contributing factors including time-based degradation of the electrical device and the at least one operating parameter. The method outputs, based on the assessing, an indication of an extent of contribution of degradation of the electrical device to the increase in power consumption.
 
Type: Grant
Filed: May 9, 2017
Date of Patent: February 11, 2020
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors: Harish Bharti, Abhay K. Patra, Pranshu Tiwari, Saurabh Trehan
Publication number: 20180356776
Abstract: A method, system and computer program product are disclosed for rewarding customers for sustained energy conservation. In embodiments of the invention, the method comprises establishing a baseline of energy consumption for a customer; defining a rewards program; and determining a reward for the customer, based on the rewards program, for maintaining the customer’s energy utilization in a given range compared to the baseline. In embodiments of the invention, the system comprises one or more processing units configured to operate as a file server for receiving specified energy consumption data from customers, and a business analytical engine. The business analytical engine stores a defined rewards program; establishes a baseline of energy consumption for one of the customers; and determines a reward for the one customer, based on the rewards program, for maintaining the one customer’s energy utilization in a given range compared to the baseline.
 
Type: Application
Filed: June 7, 2017
Publication date: December 13, 2018
Inventors: Harish Bharti, Abhay K. Patra, Pranshu Tiwari, Saurabh Trehan
Patent number: 9766693
Abstract: Provision of power scheduling framework for a plurality of virtual machines to facilitate energy savings in handing service instances includes configuring a first set of virtual machines in an active power mode and a second set of virtual machines in one or more other power modes, and managing, across a time period and based on service instance arrival, power mode configuration for the first set of virtual machines and the second set of virtual machines, the managing including initiating one or more transitions of at least one virtual machine between power modes of the plurality of power modes, wherein a transition energy cost is associated with transitioning from a lower power mode of the plurality of power modes to a higher power mode of the plurality of power modes, and wherein the managing accounts for transition energy cost in determining the one or more transitions.
 
Type: Grant
Filed: January 7, 2016
Date of Patent: September 19, 2017
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventors: Rajesh K. Saxena, Pranshu Tiwari, Vikram Yadav
Publication number: 20170017913
Abstract: In an approach to managing data quality and compliance, a computer retrieves data within a business enterprise system. The computer applies a set of rules to the data, wherein the application of the set of rules to the data produces a plurality of mapped data, and the computer aggregates the plurality of mapped data into a plurality of results. The computer then reports the plurality of results for a data display.
 
Type: Application
Filed: July 17, 2015
Publication date: January 19, 2017
Inventors: Harish Bharti, Kshitij K. Raval, Pranshu Tiwari
Publication number: 20160224965
Abstract: An approach is provided for determining an optimal payment instrument. A computer in a system configured in one of four predetermined cloud-based models updates a database with details about account balances and rewards provided by a customer’s multiple accounts specifying payment instruments. A request is received from a near field communication enabled mobile device to purchase an item from a retailer. The request includes identifications of the retailer and the item. Based on the identifications, details about the account balances and rewards are retrieved from the database. Based on the details about the account balances and rewards, rules are applied and the optimal payment instrument is determined. A display of the optimal payment instrument to the customer is initiated. The optimal payment instrument is selected and a payment for the item by the optimal payment instrument is initiated.
 
Type: Application
Filed: February 4, 2015
Publication date: August 4, 2016
Inventors: Deepak Chauhan, Pranshu Tiwari, Saurabh Trehan