Predictive-Models-for-Equipment-Fault-Detection---Secom-Dataset

Secom dataset consists of a unique scenario called 'rare-events', in which the output classes are highly imbalanced. Hence, a combination of various sampling techniques and classification models are employed in predicting the faulty equipment.

Predictive-Churn-Model-using-Artificial-Neural-Network

A predictive churn model is designed using ANN which predicts the risk of churn for every customer. Probability of churn for each individual customer will be calculated, aiding the bank to rank its customers and implement preventive measures. Predictions are made based on the probability threshold value.

Bike-sharing-system-Analysis-and-trip-prediction

Bike-sharing rental process is highly correlated with the environmental and seasonal settings. For instance, weather conditions, precipitation, day of week, season, hour of the day, etc., can affect the rental behaviors. The dataset is related to the two-year historical log (aggregated on daily basis) corresponding to years 2011 and 2012 from the Capital Bikeshare system, Washington D.C., USA. The variables are defined as follows: season 1=spring, 2=summer, 3=fall, 4=winter year 0=2011, 1=2012 month 1=Jan, 2=Feb, …., 12=Dec holiday whether the day is holiday or not (1=holiday, 0=not) weekday day of the week (0=Sun, 1=Mon, …., 6=Sat) weathersit (weather condition of the day): 1= Clear, Few clouds, Partly cloudy 2= Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist 3= Light Snow, Light rain + Thunderstorm + Scattered clouds 4= Heavy Rain + Ice pallets + Thunderstorm + Mist, Snow + Fog) temp normalized temperature in Celsius atemp normalized feeling temperature in Celsius hum normalized humidity windspeed normalized wind speed count count of users (response)