Empower Your Quantitative Trading
High-performance libraries and frameworks for quant traders, funds, and low latency application developers
Our Core Frameworks
dxcore
Core library with CUDA code, OpenMP/I and high frequency trading market making, signal, risk and portfolio strategies, in C++.
#include <dxcore/market_making.h>
#include <dxcore/signal_processing.h>
__global__ void highFrequencyStrategy(MarketData* data) {
int tid = blockIdx.x * blockDim.x + threadIdx.x;
if (tid < NUM_SECURITIES) {
float signal = computeSignal(data[tid]);
updateQuotes(data[tid], signal);
}
}dxlib
High-level functionalities, interface for Python for dxcore with methods for manipulating data, networking, storage, caching and ML.
import dxlib as dx
# Load and preprocess data
data = dx.load_market_data('AAPL', '2023-01-01', '2023-06-30')
features = dx.compute_features(data)
# Train ML model
model = dx.MLModel('RandomForest')
model.train(features, target='returns')
# Make predictions
predictions = model.predict(new_data)
dxstudio
Native app for studying contracts, analyzing investment opportunities and strategies with API interfaces for calling studio GUI methods from other applications.
from dxstudio import Studio
# Initialize dxstudio
studio = Studio()
# Load a strategy
strategy = studio.load_strategy('mean_reversion.dxs')
# Backtest the strategy
results = studio.backtest(
strategy,
start_date='2023-01-01',
end_date='2023-06-30',
capital=1000000
)
# Display results in GUI
studio.display_results(results)