Was the data stored in a flat table? Did you develop features yourself or did someone do it for you?

Data for machine learning models are often stored in flat tables (DataFrame), where each row is a separate object or observation, and columns are features. This format is convenient for most algorithms and libraries.

Regarding feature development, I usually participate in this process myself: analyzing data, creating new features, testing their impact on model quality. Sometimes, there are specialists in feature engineering in the team who develop complex or specific features, but overall I prefer to control this stage to better understand how data influence the result.

An example of simple feature creation in Python with pandas:

import pandas as pd

df = pd.DataFrame({
    'age': [25, 32, 47],
    'income': [50000, 60000, 80000]
})
# Create a new feature — age in decades
 df['age_decades'] = df['age'] // 10