Projects
-
The Future of HR Analytics Using Machine Learning to Predict and Improve Employee Performance
The work utilizes extensive employee performance data, including metrics such as productivity scores, attendance records, and peer reviews. This data is pre-processed to ensure accuracy and relevance for analysis. The methods involve selecting key variables and applying machine learning algorithms, such as regression and classification models, to predict performance outcomes. Hyperparameter tuning is performed to optimize these models. The results indicate that machine learning can significantly enhance the accuracy of performance predictions, leading to more informed HR decisions.
-
Novel Applications of Data Analytics in Financial Markets
The work uses historical financial data, including stock prices, trading volumes, and economic indicators. This data is meticulously pre-processed to ensure accuracy and relevance for analysis. The methods involve applying machine learning algorithms such as Long Short-Term Memory (LSTM), Artificial Neural Networks (ANN), and Linear Regression to identify patterns and predict market trends. The results indicate that these models significantly enhance the accuracy of market predictions, leading to better investment decisions and risk management.
-
An Analytical Hierarchical Process based Weighted Assessment of factors contributing Precipitation
The work makes use of climatic data, including maximum temperature, wind velocity, relative humidity, solar radiation, and elevation, to assess their impact on precipitation. This data is pre-processed to ensure accuracy and relevance for analysis. The methods involve applying the Analytical Hierarchical Process (AHP) to weigh these factors, addressing issues like rank reversal and uncertainty in parameter ranking. The results highlight the effectiveness of AHP in identifying key contributors to precipitation, providing valuable insights for climate modeling and prediction.
-
Flood Inundation Mapping of Lower Godavari river basin using Remote Sensing and GIS
The data from the Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM) with a 30-meter resolution, along with water level and discharge data from the lower Godavari River basin is used. This data is pre-processed to ensure accuracy and relevance for analysis. The methods involve using Remote Sensing and Geographic Information System (GIS) techniques to generate flood inundation maps, and calibrating a hydrodynamic model with historical flood data. The results indicate that the model accurately predicts flood extents, providing valuable insights for flood management and mitigation.