Involved in Fraud Risk Strategy of different financial products.
Objectives are to involve in pre and post fraud strategies, monitoring the existing rules, KPI'S and updating it for better customer experience.

Consultant 2

Synchrony

1- Credit Risk Segmentation (Machine Learning | Classification | Automation | Model Stability)

Objectives : Identify and segregate the Risk Segments, Clusters, or Natural Groups that are formed based on Data attributes.

Packages used: Numpy, Pandas, Matplotlib, Plotly, Seaborn, Scikit-Learn, Seaborn

RESPONSIBILITIES :-
1. Retrieving the data from Data Warehouses of around 500k entries using SQL, SAS, and Python .
2. Stitching and merging data on a user and portfolio level, feature-engineering for transforming interaction variables.
3. Classification algorithms like Logistic regression, Random Forest, and XGBoost have been used to generate optimum classifications.
4. XGBoost outperformed other models.
5. Validated results and performed quality assurance to ensure data accuracy.
6. Generated comprehensive business reports using statistical methods.
7. Developed Excel documents for presenting metrics data to stakeholders.

Senior Analyst

Infosys

1 - Anomaly Detection (Machine Learning | Classification | Automation)

Objectives : Identify and flag the anomaly based on user activities associated with an assigned system having consumer transaction data.

Packages used: Numpy, Pandas, Matplotlib, Seaborn, Scikit-Learn, Scipy, Sklearn, Plotly

RESPONSIBILITIES :- 
1. Retrieving the data from Data Warehouses of around 200k entries using SQL, Python. 
2. Based on live streaming data, created a Knowledge base contains classifications based on departments, persons, and OS.
3. Classification algorithms like Logistic regression, Random Forest, Naive Bayes, and XGBoost have been used to generate optimum classifications.
4. Used Confusion Matrix to display the model performance. gained Recall measures of 0.83 to detect the positive samples.


2 - Application Crash Prediction (Machine Learning | Classification | Clustering | Automation)

Objectives : Identify and flag the application crash based on CPU usage, I0 usage, and memory consumption can have a significant impact on the performance of the application.

Packages used: Numpy, Pandas, Matplotlib, Seaborn, Scikit-Learn, Scipy, Sklearn, Plotly

RESPONSIBILITIES :-
1. Retrieving the data from Data Warehouses of around 200k entries using SQL, Python.
2. Classification algorithms like Logistic regression, Random Forest, Naive Bayes, and XGBoost have been used to generate optimum classifications. Built the classification model to proactively alert the users on possible application failure/ unresponsive scenarios.
3. Applied cross validation of evaluation metrics with 79% accuracy, 0.86 Recall.

Senior System Engineer

Experience of working under Analytics Unit at Infosys.
My work consits the uses of Machine Learning and it's Algorithms, Statistical analysis and Inferences,
Data Understanding, Data Filtering and Cleaning, Exploratory Data Analysis, Feature Engineering, Statistical and Predictive Modeling ,Optimization and Deployment.
I also have basic understanding and experience of working on Pyspark on Data Bricks,Rule Minning and Associstions".

System Engineer

Got regrious training in the uses of Machine Learning and it's Algorithms, Statistical analysis and Inferences,
Data Understanding, Data Filtering and Cleaning, Exploratory Data Analysis, Feature Engineering, Statistical and Predictive Modeling ,Optimization and Deployment.
Got hands-on experiences on Mysql.
worked on Credit card dummy data set and applied Clustering algorithms to label yes and no for issuing the Credit card.

Intern

IRIS IIM Indore

Campus Ambassador of SRM University at IIM Indore

Campus Ambassador

• Data Scientist with experience in providing Data-Driven solutions with a strong track record in end-to-end Data Pipelines and delivering Machine Learning solutions.

• Equipped with strong understanding and expertise in Python and SQL, with a focus on Model Development and Statistical Inference to drive business needs and impactful projects.

• Proficient in hands-on Predective and Statistical Modeling, Data Visualization Techniques and harnessing unsupervised NLP techniques for informed insight.

• Demonstrated ability to translate business problems into analytical solutions that drive business growth and enhance customer satisfaction.
 
• Strong communication and collaboration skills with a proven track record of presenting insightful reports and presentations to diverse stakeholders.

Advocate of responsible AI.

Taplio

Prateek Kumar's Linkedin Analytics

Want to drive more opportunities from LinkedIn?

Taplio

.css-1jgreyo{background-image:linear-gradient(284deg, rgba(39,43,72,1) 0%, rgba(33,47,183,1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}Prateek Kumar's Linkedin Analytics

Want to drive more opportunities from LinkedIn?

Prateek Kumar's Linkedin Analytics