The report presents with the development and optimisation of an enhanced algorithmic trading strategy through the use of historical S&P 500 market data and earnings call sentiment analysis. The proposed strategy integrates various technical indicators such as moving averages, momentum, volatility, and FinBERT-based sentiment analysis to improve overall trades being taken. The results show that the enhanced strategy significantly outperforms the baseline model in terms of total return, Sharpe ratio, and drawdown amongst other factors. The findings helped demonstrate the relevance and effectiveness of combining technical indicators, sentiment analysis, and computational optimisation in algorithmic trading systems.
Figures & tables
Dataset
Strategy
Total Return
Sharpe Ratio
Maximum Drawdown
Win Rate
Volatility
Development
Baseline
299.84%
1.19
-57.41%
33.30%
37.05%
Development
Enhanced
466.14%
1.69
-23.08%
46.60%
30.28%
Validation
Baseline
12.45%
0.41
-35.42%
27.75%
43.80%
Validation
Enhanced
189.10%
2.04
-23.50%
38.50%
40.00%
Test
Enhanced
152.40%
2.07
-13.5%
41.0%
26.10%
Table 1: Performance Comparison of Baseline and Enhanced Strategies on All Datasets
Figure 1: Baseline vs Enhanced Strategy Comparison
Figure A1: 63-Day Momentum vs Forward 21-Day Return
Figure A2: Cumulative Returns: Top Momentum Portfolio vs Market Average
Figure A3: ATR(14) Volatility vs Forward 21-Day Return
Figure A4: Momentum Deciles vs Average 21-Day Forward Return
Figure A5: ATR Volatility Buckets vs Average 21-Day Forward Return
Figure A6: Momentum-to-Volatility Ratio Deciles vs Average 21-Day Forward Return