Devamani Chowdary P

Seasoned collaborator experienced in meeting needs, improving processes and exceeding requirements in team environments. Diligent worker with strong communication and task prioritization skills.

Forecasting the Demand on bike Rentals.
→ Forecasted the demand for bike rentals based on time series forecasting analysis, accurately Predicting the demand, maintenance cost, profits.
→ Exploratory data analysis was done and testing was done to build Holts - winter, SARIMA, seasonal Naive and neural networks models.
→ We found all the metrics of NN are better than SARIMA, Thus we consider NN to forecast he future demand.

Reducing Fraud Transactions.

→ To reduce the bank fraud transactions logistic regression was conducted within the dataset. Along with regression model we have conducted Random forest model & Decision classifier model.
→ Trained the model with 80% of data and feeded our model with 20% of the test data. Predicted data is compared with y test data and when these values are similar, we get the high the accuracy.