The Hark Blog - Archive

Timeseries Stationarity

Timeseries Stationarity

This blog post discusses the importance of stationarity in timeseries data when performing analysis or generating forecasts. Non-stationary data can pose challenges for accurate forecasting, but transformations such as differencing, Box-Cox, and Yeo-Johnson can help make data stationary. These techniques can help with effective planning and implementation of energy management policies.

Read More
data science image

Understanding the Bias Variance Trade-Off

The bias-variance trade-off is a fundamental concept in machine learning and statistics that refers to the trade-off between a model’s ability to fit the training data well (low bias) and its ability to generalise to unseen data (low variance).

Read More
Splitting data

Splitting data into ‘train’, ‘validation’ and ‘test’ sets

When developing and deploying machine learning models, it’s important that we split the dataset into ‘train’, ‘validation’, and ‘test’ datasets. This protects against an overfitted model, and helps ensure results are generalised. In this blog post we will look in to how to split the data, and why.

Read More
Energy Baselining

What Are Energy Baselines (EnB)?

Energy Baselines are another great tool for tracking energy performance. They define reference periods before and after energy efficiency projects have been implemented.

Read More

Subscribe to Our Newsletter

Stay up to date with the latest industry news, platform developments and more.