Planning stock portfolios is a challenging task, because investors have to forecast stock market trends. To limit losses due to wrong forecasts a common strategy is diversification, which consists in buying stocks belonging to different sectors/markets to spread bets across different assets. Since the amount of stock market data is continuously growing, an appealing research strategy is to first apply data mining algorithms to discover significant patterns from potentially large stock datasets and then exploit them to support investor decision-making. This article presents an itemset-based approach to supporting buy-and-hold investors in technical anal- yses by automatically identifying promising sets of high-yield yet diversified stocks to buy. Specifically, it investigates the use of itemsets to generate stock portfolios from historical stock data and recommend them for buy-and-hold investments. To achieve this goal, it analyzes stock market datasets, which contain for each stock the closing prices on different trading days. Datasets are enriched with (analyst-provided) taxonomies, which are used to classify stocks as the corresponding sectors. Unlike previous approaches, it generates a model composed of a subset of potentially interesting itemsets, which are then used to support investors in decision-making. The selected itemsets represent promptly usable stock portfolios satisfying expert’s requirements on minimal average return and minimal level of diversification across sectors. The experiments performed on real stock datasets acquired under different market conditions demon- strate the effectiveness of the proposed approach compared to real stock funds.
|Titolo:||Planning stock portfolios by means of weighted frequent itemsets|
|Data di pubblicazione:||2017|
|Digital Object Identifier (DOI):||10.1016/j.eswa.2017.05.051|
|Appare nelle tipologie:||1.1 Articolo in rivista|