Scribd
Upload
36 views3 pages

Shivdip Dilip Deshmukh: Data Scientist at TCS

Uploaded by

007shri007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views3 pages

Shivdip Dilip Deshmukh: Data Scientist at TCS

Uploaded by

007shri007
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Shivdip Dilip Deshmukh

Data Scientist at TCS.

Professional Summary:
Open-minded Data Scientist with 3+ years of experience. Experience in executive data-driven solutions to increase efficiency, accuracy, and
utility of data processing. Knowledge of gathering, cleaning, and organizing data. Proficient in predictive modelling, data preprocessing,
Machine Learning Algorithms, Deep Learning Neural Networks as well as scripting language Python to solve Industrial problems. Advanced
understanding of Algebraic, Statistical, and other analytical techniques. Highly organized, motivated, process oriented and diligent with
significant background in mathematics.

Professional Skills:

 Expertise in Data Analysis, statistics, programming and ML techniques.


 Expertise in Python programming language.
 Experience in creating mature Data science pipelines encompassing Data standardization, Feature extraction, model validation and
optimization.
 Cleaned, merged and manipulated datasets and conducted feature engineering using Pandas.
 Hands-on experience of Data Science libraries in Python such as Pandas, NumPy, scikit-learn, Matplotlib, seaborn, Keras, OpenCV,
TensorFlow.
 Novice knowledge in Python framework (like Django, Flask etc)
 Experienced in Visualization Tools Like Tableau, PowerBI.
 Having experience in aws cloud and working on lambda functions is preferable.
 Experienced with Git and version control best practices.
 Experience with scripting in SQL - extracting large data sets and design of ETL flows.
 Knowledge of Big Data Concepts and Hadoop, MapReduce, Spark
 Experienced with various SDLC processes and methodologies.
 Experienced in Agile development.
 Having strong knowledge of Data Structure and Algorithms
 Good problem-solving skills, Positive attitude, self-motivated and Quick learner

Employment History:
Data scientist at TCS
Period: Nov 2020 to Dec 2023
Analytics Consultant at Infiniti Research
Period: Jun 2024 till present.

Projects:
Company: Infiniti Research (Bangalore)
Project 1: Develop the predictive model for forecasting the receivables and payables for upcoming months
Client: AB-InBev Jun 2024 – present
Domain: GPS (Goods Packaged Services)
Primary Goal: Design the predictive model to calculate the MSB (Minimum support balance) for each zone.
Skills used: Data Pre-processing, Data Visualization, EDA, Model training and evaluation using a supervised machine learning algorithm.
Roles and responsibilities:
• Explore and understand the dataset. Identifying patterns and trends.
• Clean and pre-process data to ensure its quality and relevance.
• Develop predictive models for estimating receivables and payables amount based on historical and real-time data.
• Choosing important features for the further analysis as per client’s specifications and Utilize machine learning algorithms to analyse
factors affecting delivery performance.
• Take feedback from analysis, end-users, and domain experts to perform model calibration, bug fixes, and enhancements.
• Continuously refine and improve predictive models based on feedback and evolving data patterns.
• Collaborate with operation teams to get the ad-hoc business need.
• Use analytics to ensure efficient reduction in deviation between model predicted values and actuals from ad-hoc business.
• By using combination of supervised machine learning recursive model output approach and time series models able to reduce the
delta of our model from 43% (business metrics) to 19% which is the achievement of our team.
• Documentation of project and model.

Project 2: Prediction of Probable Backorder Scenarios in the Supply Chain.


Client: Quality North Carolina Jun 2023 - Dec 2023
Domain: E-commerce
Primary Goal: To build a predictive model to improve the efficiency and reliability of supply chain by anticipating potential backorder
situations by early detection of where backorders are likely to occur.
Skills used: – Data Exploration, Feature Engineering, Data Visualization, EDA, Model Building, pre- and post-performance checking
Roles and responsibilities:
• Enhancing data collection procedures and pipelines to include information that is relevant for building analytic systems.
• Explore and understand the dataset, including historical demand inventory levels and order fulfilment dates.
• Clean and pre-process data to ensure its quality, consistency, and relevance of predicting modelling.
• Identify and engineer relevant features that contribute to the prediction of backorder scenarios.
• Extract meaningful information from the data to enhance the performance of predictive models.
• Evaluate model performance using metrics such as precision, recall, F1 score or area under the ROC curve.
• Collaborate with supply chain experts to develop optimization strategies.
• Provide insights on how to adjust inventory levels, reorder points and supply chain processes to minimize backorder risks.

Project 3: AI Model for Auto Resume Screening Solution for HR department


Client: Zenjob, Netherland Jan 2023 – May 2023
Domain: Human Resource Department
Primary Goal: To create an AI system to handle automatic resume screening process.
Techniques used: Data Mining, Data Cleaning, Data Exploration, Feature Engineering, Data Visualization, ML model building.
Roles and responsibilities:
• Responsible for designing, implementing, monitoring, and maintaining our machine learning systems that forecast the response
variable.
• Perform relevant modelling analysis and POC exploring multiple techniques to Ensure Analytic model quality.
• Perform Exploratory Data Analysis and Statistical Analysis; clearly present the results of an analysis to customers and management.
• Analyse large amounts of information to discover trends and patterns.
• Combine models through ensemble modelling.
• To develop machine learning algorithms for physical fitness devices using a local Windows PC and DGX/cloud GPU

Project 4: Farming Assistance Prediction Framework for Soil Fertility Improvement and Crop Prediction
Client: Tony, Pennsylvania Sept 2022 – Dec 2022
Domain: Precision Farming Department
Primary Goal: To analyse factors affecting crop growth and suggest suitable crop as per the weather and soil conditions.
Techniques used: Data Cleaning, Data Exploration, Data Visualization, ML model building.
Roles and responsibilities:
• Collect and pre-process relevant data for soil fertility and crop prediction.
• Design and implement machine learning models for crop prediction.
• Collaborate with domain experts to refine models based on agricultural knowledge.
• Perform Exploratory Data Analysis and Statistical Analysis.
• Analyse large amounts of information to discover trends and patterns.
• Evaluate model performance and make necessary adjustment.

Education:
Bachelor of Mechanical Engineering from DRIEMS

Certifications:
• IBM Certified Data Science Professional Certification
• Certified Python 3.4.3 programmer by Code Nucleya, an IBM initiative
• Introduction to Data Analytics on Amazon Web Services AWS introductory certification • TCS’s Digital Learning Hub TCSiONCertified
Career Edge Achiever April 2021

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy