Skip to content

ArvindRoshaan/hackathon-time-series-regression

Repository files navigation

Hyderabad City Power Consumptions

Predict power consumption across three zones in the city by the Electricity board of Hyderabad (Kaggle Link)

Description

You have been hired as a Data science consultant by the Electricity board of Hyderabad to predict power consumption across three zones across the city. Your forecasts will help the electricity board to plan for the projected electricity requirements and make necessary agreements to avoid at shortfall of power to the city. You’ll develop models trained on historical power consumption data across the three zones. Besides the power consumption data, you will also have some other parameters that can impact the power consumption in a region. With reasonable efforts, you should be able to get to a MAPE performance of less than 6%.

Evaluation

Submissions are evaluated on MAPE (Mean Absolute Percentage Error) between predicted and actual values. Final evaluation metric is the mean of the MAPEs calculated for three zones

Contents of the submission notebook (image attached)

image

Prediction

image

Submission Format

For each DateTime you must predict the power consumption for all 3 zones. The file should contain a header and have the following format: DateTime, Zone 1 Power Consumption, Zone 2 Power Consumption, Zone 3 Power Consumption 2017-12-01 00:00:00,37237.94,28259.26,38923.04 2017-12-01 00:10:00,16652.03,26271.69,22312.31 2017-12-01 00:20:00,31705.53,30985.58,23373.82 2017-12-01 00:30:00,46446.41,23514.69,6275.89 etc.

Citation

0812, udheep, vaibhaw khemka. (2023). Hyderabad City Power Consumptions. Kaggle. https://kaggle.com/competitions/hyderabad-city-power-consumptions

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published