Akshat111111 / Hedging-of-Financial-Derivatives

This strategy works for every market condition irrespective of the movement
BSD 3-Clause "New" or "Revised" License
75 stars 100 forks source link

💡[FEATURE]: Enhancing Feature Engineering for Crisis Prediction #266

Closed FreeSpirit11 closed 4 months ago

FreeSpirit11 commented 4 months ago

Enhancing Feature Engineering for Banking Crisis Prediction Model

Description: The code introduces several feature engineering techniques to improve the predictive performance of the banking crisis prediction model.

  1. Interaction Terms: Multiplication of 'systemic_crisis' and 'domestic_debt_in_default' to capture their interaction effect.
  2. Ratio Features: Calculation of the ratio between 'exch_usd' and 'inflation_annual_cpi' to provide a normalized exchange rate.
  3. Moving Averages: Computation of the 3-month moving average of 'gdp_weighted_default' to smooth out short-term fluctuations.
  4. Difference Features: Calculation of the difference in 'inflation_annual_cpi' between consecutive years to capture changes over time.
  5. Categorical Aggregations: Aggregation of mean inflation rates for each level of the 'banking_crisis' variable to provide additional insights.

These feature engineering techniques aim to extract more meaningful information from the existing data, potentially enhancing the model's ability to predict banking crises in African economies.

FreeSpirit11 commented 4 months ago

Hi @Akshat111111 , I have raised this issue. Please assign it to me.