Quant Fidelity Fixed Income Asset Allocation Model

Framework fixed income asset allocation model.py

import pandas as pd
import matplotlib.pyplot as plt
import yfinance as yf
import requests

# Load the data for the macro, fundamentals, sentiment, and valuation pillars
macro_data = pd.read_csv('macro_data.csv')
fundamentals_data = pd.read_csv('fundamentals_data.csv')
sentiment_data = pd.read_csv('sentiment_data.csv')
valuation_data = pd.read_csv('valuation_data.csv')

# Normalize and truncate the data for each pillar
for pillar_data in [macro_data, fundamentals_data, sentiment_data, valuation_data]:
    pillar_data = (pillar_data - pillar_data.mean()) / pillar_data.std()
    pillar_data = pillar_data.clip(-2, 2)

# Round the data for each pillar to the nearest 0.5
for pillar_data in [macro_data, fundamentals_data, sentiment_data, valuation_data]:
    pillar_data = pillar_data.round(0.5)

# Load the information ratios for each indicator
info_ratios = pd.read_csv('info_ratios.csv')

# Weight the indicators based on their information ratios
macro_weights = macro_data * info_ratios['macro']
fundamentals_weights = fundamentals_data * info_ratios['fundamentals']
sentiment_weights = sentiment_data * info_ratios['sentiment']
valuation_weights = valuation_data * info_ratios['valuation']

# Calculate the final scores for each pillar
macro_score = macro_weights.sum(axis=1)
fundamentals_score = fundamentals_weights.sum(axis=1)
sentiment_score = sentiment_weights.sum(axis=1)
valuation_score = valuation_weights.sum(axis=1)

# Print the final scores
print('Macro score:', macro_score)
print('Fundamentals score:', fundamentals_score)
print('Sentiment score:', sentiment_score)
print('Valuation score:', valuation_score)

# Visualize the scores over time
plt.plot(macro_score, label='Macro')
plt.plot(fundamentals_score, label='Fundamentals')
plt.plot(sentiment_score, label='Sentiment')
plt.plot(valuation_score, label='Valuation')
plt.legend()
plt.show()