Data Scientist
Location : Jaipur
Experience : 4 Year
Rate: $20 / Hourly
Availability : 1 Week
Work From : Any
Category : Information Technology & Services
Page 1 of 3 Surendra-Data Scientist-4Years PROFILE SUMMARY: Achievement-driven professional experience of 4+ years. Proven ability of experience in Software Development, Project Implementation and experience as Data Scientist. Programming Languages: Python ,Pyspark, SQL. Skilled in libraries such as Sklearn, Numpy, Pandas, Matplotlib, Fbprophet, Pyod,NLTK. Having good domain knowledge of Authorizations in banking domain. Strong knowledge on Feature Engineering & Feature Selection. Good Exposure to Data Structures with Python. Cloud Platform: Azure, Heroku. Platforms and Misc: Anaconda, Jupyter Notebook, Data bricks. EXPERIENCE PROFILE: Working as Data Scientist since 2021 Oct to till Date. Worked as Data Scientist since 2018 Jun to 2021 Oct. TECHNICAL SKILLS: ML Toolbox: Numpy, Matplotlib, NLTK, Keras, Sklearn, Pandas. Python: Python, Flask, Data structures, MySQL and HTML basics. Deployment Tools: Heroku. Areas of Interests: Machine Learning, Natural Language Processing, Deep Learning. Projects Project Name: Demand Forecasting Overview: The use case is to forecast demand of the beer industry which will increase the profitability to organization. Roles & Responsibilities: Responsible for delivering the forecast for 10 countries. Interacted directly with stake holders and discussed the results. Performed statistical analysis on the forecasted results. Implemented pipeline across the granular level (channel-brand- pack-region). Forecasted the data using sarimax, xgboost, linear, log-log etc. Implemented end to end forecasting pipeline for SAZ region in azure data bricks. Page 2 of 3 Implemented outlier detection techniques IQR, zscore to detect anomalies in the forecasted data as well as in training data. Maintained and ran jobs in the data bricks platform. Project Name: Business Growth Forecasting Overview: The use case is to know which building block contribute what percentage towards that sales value. Forecasted each building block of the sales individually. Roles & Responsibilities: Participated in Data Preprocessing Techniques in order to make data useful for creating Models. Involved in migration of data from one workspace to another workspace in azure data bricks. Forecasted the data with various models like Arima, sarimax, silverkite, fbprophet. Implemented a champion challenger model for each building block. Project Name: Anomaly Detection on sales Overview: Predicting the anomalies on the sales data at sams clubs in Walmart so that client know what products on particular club will be completed. Roles & Responsibilities: Involved in understanding the Business Requirement. Participated in Data Preprocessing Techniques in order to make data useful for creating Models. Handled the seasonality of the data. Implemented few custom methods which will detect anomalies using pyod packages. Detected outlier using Isolation Forest, HBOS methods. Performed Unit testing and Integrate testing. Project Name: CAS Authorization Overview: Credit Authorization System is a TPF based application used by the client to authorize the credit card transactions. Forecasted number of requests coming to the system which will be used to increase the availability of resources to process them. Roles & Responsibilities: Involved in understanding the Business Requirement. Participated in Data Preprocessing Techniques to make data useful for creating Models. Handled the seasonality of the data. Applied differencing technique to make the data stable. Forecasted the data using the fbprophet. Page 3 of 3 Project Name: Treatment plan Recommendation Overview: TMC is the preferred contract therapy and rehab management provider making a positive difference by delivering compassionate, superior care. The Client needs an algorithm to recommend a treatment plan for a patient at the time of his admission. Roles & Responsibilities: Experience in Data Analysis, visualization, statistics, programming and Machine Learning techniques. Extensive Model building experience with Machine Learning algorithms for Product Experience in creating mature Data science pipelines encompassing Data standardization, Feature extraction, model validation and optimization Exploring and visualizing data to drive insights Importing data from SQL Server. Experienced in feature selection using filter methods, wrapper methods and feature importance. Advance knowledge of ML algorithms such as Matrix Factorization, Clustering, Grid search, Random Forest, Decision Tree, SVM, Cross Validation, KFold. Hyper-parameter tuning to improve the model Validation metric for Regression and classification algorithms including classification report Participating in constant learning through training and skills development *******THANKS*******
{{contact.cdata.phone}}
{{contact.cdata.email}}
View Resume
