Job_loss % Due to Ai:
-
Data collection: Data collected from kaggle,it contains percentage value (%)of the AI_adoption rate,Job loss,Human-Ai collaboration,Revenue increase,Market share,Customer_trust,category of Country,Industry,Regulation_status,TOP-AI tools and Year.
-
Data Handle: Pandas to read the dataset,checking null values,describe to statistical report (Mean,Standard Deviation,Max,min,etc...)for each numerical value columns.
-
Data encoding: Use
pd_dummiesto encoding the categorical columns like "Country","Industry","Regulation status","Ai tools". -
Data split: Data Features(without Target column) and Taget(job_loss %)
-
Algorithm: Used algorithms
Linear Regression and Random Forest Regression -
Model save: Model saved in pickle file for future prediction.
-
Result: Random Forest had less
R^2 score (~ -1.17) and Mean squared Error (~230)work well in this job_loss prediction. -
Dashboard Power BI interactive dashboard for visual insights:
[Autoregressive Integrated Moving Average]:
Industry revenue forecasting using ARIMA:
Statsmodel of ARIMA for Revenue time series forecasting -
ForecastData: same data to slicing year and Revenue columns.
-
Forecast: ARIMA model to forecast for Revenue Increase% over the future years. Arima work well on the more datapoints.
