Using Polynomial Models to Forecast Financial Assets Behavior

This chapter proves that polynomial models are effective in predicting intraday movement of financial assets. We apply a Polynomial Auto Regression (PAR) model to intraday price data of four major crypto currencies forecast intraday price volatility and convert the model into a real-time profitable automated trading system. Financial risk refers to the uncertainty of investment results that is affected by one or more random factors, including operational risk, credit risk, exchange rate risk and market risk. A PAR model was constructed to fit crypto currencies' behavior and to attempt to predict their short-term trends and trade them profitably. We employed machine learning (ML) techniques to train our system utilizing minutes' worth of data for six months, and then we used it to carry out lucrative trading and report for the next six months. The buy and hold (B&H) approach was significantly outperformed by our system for each of the four crypto currencies that were studied, according to the results. Results show that our system's best performances were achieved trading Ethereum and Bitcoin and worse trading Cardano. Our trading system used six months of training to identify the best fit polynomial model for the examined cryptocurrencies. Moreover, the system has optimized the percentage deviation from the prediction line that will guide the trade entrance. The highest net profit (NP) for Bitcoin trades was 15.58%, achieved by using 67 minutes bars to form the prediction model, compared to -44.8% for the B&H strategy. Trading Ethereum, the system generated 16.98% NP, compared to -33.6% for the B&H strategy, 61 minutes bars. Moreover, the highest NPs achieved trading Binance Coin (BNB) and Cardano were 9.33% and 4.26%, compared to 0.28% and -41.8% for the B&H strategy, respectively. Furthermore, the system better predicted Ethereum and Cardano uptrends than downtrends while it better predicted Bitcoin and BNB downtrends than uptrends. Additionally, for every cryptocurrency, the system found a distinct optimal arrangement. Additionally, the algorithm performed better on long trades for Ethereum and Cardano than on short transactions, and better on short trades for Bitcoin and BNB than on long trades.