Welcome to Data Science In Action
Hi,
Welcome to my website. I am a trained engineer, statistician with passion in machine learning, artificial intelligence.
Solve the real world problems and add value to your team by using my expertise and business experiences.
Please feel free to contact me: stanghong@gmail.com
Hong
Data Visualization
Data Query, Visualization and PowerBI Dashboards
Power query and SQL queries to enable sustainable data cleaning
Dynamic filter, join, merge, groupby data allow interactive slice and dice large data set and extract insights
Python based machine learning algorithm reduce cycle time and improve business decision quality
Industry Machine Learning Projects
ML significantly improve efficiency
Use PCA and ML methods, we are able to reduce data processing time from days to hours
High prediction accuracy enables timely business decision and great cost saving
EDA of real health app data to improve customer engagement during holiday season
Smart Drilling from ML study
Successful application of neural network for rock facies classification in a carbonate field saved million dollars in infill drilling and data acquisition
Big discovery from ML Prediction
Successful application of classification and geostatistics methods results in a big discovery of a volcanic clastic reservoir
ML model to predict show-no show for hospital appointments
Multiple methods for feature engineering, feature selection, model selection, hyperparameter tunning and finally model development
Classification Hands on Projects
More on Neural Network and Parameter Tuning
Recommendation System
Regression, Dimension Reduction and Fun
Learning Journey
Skills
§ Programming Languages
Python(NumPy, Pandas, Seaborn, Scikit-learn), R, SAS, MATLAB, C, VBA
§ ML Algorithms (Proficient)
Regression, Discriminate analysis, Clustering analysis, PCA
KNN, Support Vector Machine, Decision Tree, Random Forrest, Naïve Bayes
Artificial Neural Network (Back Propagation, Probabilistic Neural Network)
§ ML Algorithms (Skillful/Aware)
XGBoost, NLP, CNN, Time Series Analysis, DataBot (H2O), Tensorflow, Recommendation System
§ Query/ Visualization
SQL, Power Query /Power BI, Spotfire
§ Other Statistic Tools
Experimental Design, Response Surface, ANOVA, Monte-Carlo Simulation, Multipoint Statistics, Sequential Gaussian Simulation, Object based modeling