Looking for a job

Nikhil Korane

@nikhilkorane

Machine Learning Engineer at Netcracker Technology building telecom churn models on 1M+ subscriber records.

At Netcracker Technology, I designed a customer churn prediction model for a telecom BSS platform, combining Scikit-Learn, XGBoost, and neural network classifiers. I engineered features from 1M+ subscriber records and evaluated model variants with cross-validation and precision-recall analysis.

Previously, at Lenovo PCCW Solutions, I developed predictive models for IoT datasets and improved analytical throughput by 35% through preprocessing optimisation. At Amdocs, I built data quality, reconciliation, and ETL tooling that reduced runtime by 30% and achieved 99.99% accuracy.

Experience

Work history, roles, and key accomplishments

Current

Technical Business Analyst

Current

Netcracker Technology

May 2023 - Present (3 years 5 months)

Designed and developed a customer churn prediction model for a telecom BSS platform using an ensemble approach, achieving significant improvement in churn identification accuracy. Engineered feature pipelines and statistical validation frameworks for 1M+ record datasets.

scikit learn XGBoost Neural Networks EDA Feature Engineering Hypothesis Testing Python SQL Data Pipelines Anomaly Detection Cross Validation Precision Recall Analysis

Data Scientist

Lenovo PCCW Solutions

Sep 2020 - Apr 2023 (2 years 7 months)

Developed predictive models on large-scale IoT datasets using Python and ML techniques, owning the full lifecycle from problem formulation to production deployment. Designed feature engineering pipelines and improved analytical throughput by 35% through preprocessing optimisation.

Python Machine Learning Feature Engineering Backtesting data preprocessing Model Evaluation Dashboarding IoT Analytics

Software Developer

Amdocs

Jan 2016 - Aug 2020 (4 years 7 months)

Built automated data quality, reconciliation, and ETL tooling for large-scale data pipelines, reducing runtime by 30% and achieving 99.99% accuracy. Operated in high-stakes production environments ensuring data correctness for downstream analytical and ML workloads.

Data Quality ETL Data Pipelines Reconciliations Automation Python SQL