Cryptocurrencies are a cryptography based technology, that has increased massively in popularity in recent years. These currencies are traded on markets that specialize in cryptocurrency trade. There, you can trade one cryptocurrency for another, or buy one with real world money. These markets are quite volatile, meaning that the price of most cryptocurrencies swing up and down a lot. The largest cryptocurrency is Bitcoin, but there is also more than 1500 smaller ones, that goes by the name alternative coins, or altcoins. This thesis will try to find out if it is possible to make accurate predictions about the future price of the altcoin Ethereum, and also see if Bitcoin may have some influence over the price of the selected altcoin. The predictions were made with the use of an artificial neural network, an LSTM network, that was trained on labeled data from 2017. The predictions were then made in intervals of one hour ahead, six hours ahead, and one day ahead through early 2018. The predictions showed that it is possible to make somewhat accurate predictions about the future. The predictions that were made one hour ahead were more accurate than both the six hours ahead predictions and the full day ahead predictions. By comparing the loss rates of the neural networks that were only trained on Ethereum, with the loss rates of the networks that trained on both Bitcoin and Ethereum, is was made clear that training on both cryptocurrencies did not improve the prediction accuracies.

This thesis extends the 52-week high momentum literature, which was first published by George and Hwang in 2004, by stressing the parameters of the trading strategy to investigate its robustness. George and Hwang, in their seminal paper, find that the ratio of a stock’s close price to its 52-week high price is a good predictor of future returns. The thesis stresses various parameters of the strategy - such as the percent of total stocks bought and sold each period – and applies the strategy over different time periods – such as bull and bear markets. The study finds that the strategy is more profitable over the later half of the data set due to underperformance in bear markets such as the 1929 market crash and subsequent Great Depression. The results also show a significant difference in profitability between bull and bear market periods. The second half of the thesis looks at a new area in momentum, the absolute 52-week high. The strategy buys stocks whose price has increased over the previous six months, and who also close to their 52-week high price. Stocks are only bought (sold) if their price has increased (decreased) over the past six months and is close to (far from) the 52-week high price. The aim is to cut out stocks that are considered to be underperforming in the 52-week high momentum strategy, leaving only true winner and loser stocks. This strategy was found to increase the strength of the 52-week high momentum strategy, and the results show that there is no longer a significant difference between bull and bear market returns.