Given that futures contracts have short durations, data manipulation is needed to create longer price history for back testing when developing forecasting models. Various approaches have been used to develop longer datasets, each with its own advantages and disadvantages. A research study was conducted to investigate three different approaches for creating longer and continuous soybean futures datasets: the Gann method, the nearest-contract method, and the back-adjusted contract method. Although the Gann method has received little recognition due to possible disadvantages with the rolling methods, low volume, and low open interest, the results show that creating a Gann contract rolled in the manner proposed creates a method that is a viable alternative to the other approaches tested for long-term trading.
- Electronic trading,
- Forecasting,
- Neural networks,
- Data manipulations,
- Forecasting models,
- Futures contract,
- Open interest,
- Research studies,
- Rolling methods,
- Short durations,
- Soybean futures,
- Contracts,
- Gann contracts,
- Rolling contracts,
- Soybean futures
Available at: http://works.bepress.com/david-enke/40/