I am a data scientist with extensive experience working in bio-pharmaceutical and healthcare industries. I specialize in developing solutions based on artificial intelligence (AI), machine learning (ML) and deep learning (DL) to solve varied business problems.
I am a professional data scientist with 8 years of experience in the pharmaceutical, healthcare and life sciences industries. I have participated in 4 hackathons and have been a finalist in every single one of them. I have also won 2 of these 4 hackathons and work with the mindset to bring innovative ways of problem solving.
I work with the 3 Is at the core of my work ethic:
Investigate
Introspect
Innovate
My specialization includes the following areas of business:
Segmentation
Forecasting
Impact assessment
Driver analysis
Disease detection
Market Mix Modeling
Sequencing
NLP
Within the data science, AI and machine learning domain, I am adept at the following aspects:
Data quality and sanity checks
Data cleaning, preparation, transformation, evaluation
Creation of analytical datasets
Exploratory data analysis
Feature elimination, engineering, selection
Dimensionality reduction
Unsupervised machine learning: Clustering
Supervised machine learning: Classification, Regression
Time series forecasting
Wordcloud creation
Sentiment analysis
Sequencing algorithms
Geospatial models
I use RStudio as my preferred platform and R as the preferred language for data science projects.
I am adept at the following things:
1. Segmentation & Targeting (Physicians, Patients, Hospitals, Pharmacies)
2. Supply Chain Analytics (Lead Time Analysis, Segmentation, Cost-to-Serve, Go-to-Market Strategy)
3. Machine Learning (Classification & Regression)
4. Geo-spatial Models (Haversine Distance, Air Distance, Road Distance)
5. Scoring Models (Weighted Matrix Scoring)
6. R and RStudio
7. Excel
8. VBA
I have extensive experience with machine learning algorithms like:
1. Random Forest
2. Gradient Boosted Trees (GBM)
3. Linear Regression
4. Multinomial Logistic Regression
5. Artificial Neural Networks
6. XGB
7. k-means
8. Hierarchical Clustering
9. LCA
10. Cross-Validation (LOOCV, LGOCV, k-fold)
11. Sampling (SMOTE, Over, Under)