Purpose: Investment is the allocation of funds with the aim of obtaining profits in the future. An example of the investment instruments with high returns and high risks are stocks. The risks associated with the investment can be reduced by forming a portfolio of quality stocks optimized through mean-variance (MV). This is necessary because successful selection of high-quality stocks depends on the future performance which can be determined through accurate price prediction.
Methods: Stock price can be predicted through the adoption of different forms of deep learning methods. Therefore, BiLSTM and LSTM models were applied in this research using the stocks listed on the LQ45 index as case study.
Result: The utilization of LSTM and BiLSTM models for stock price prediction produced favorable outcomes. It was observed that BiLSTM outperformed LSTM by achieving an average MAPE value of 2.1765, MAE of 104.05, and RMSE of 139.04. The model was subsequently applied to predict a set of stocks with the most promising returns which were later incorporated into the portfolio and further optimized using the Mean-Variance (MV). The results from the optimization and evaluation of the portfolio showed that the BiLSTM+MV strategy proposed had the highest Sharpe Ratio value at k=4 compared to the other models. The stocks found in the optimal portfolio were BRPT with a weight of 19.7%, ACES had 16.9%, MAPI 11.8%, and BMRI at 51.6%.
Novelty: This research conducted a novel comparison of LSTM and BiLSTM models for the prediction of stock prices of companies listed in the LQ45 index which were further used to construct a portfolio. Past research showed that the development of portfolios based on predictions was not popular.

Purpose: The presence of a two-month lag in Hotel Room Occupancy Rate (TPK) data necessitates an alternative method to accommodate adjustments in the economic circumstances of the tourism industry. In this context, TPK is connected to the influx of tourists, making the data a valuable resource for assessing the tourism potential of a particular area. The information can be used to make informed decisions when considering investments in the local tourism industry. Therefore, this research aimed to formulate predictions for future trends using now-forecasting. The variables of Google Trends Index (IGT) and online traveler reviews considered were obtained from big data.
Methods: This research used machine learning methods with Random Forest, LSTM, and CNN-BiLSTM-Attention models in determining the best model. Meanwhile, the datasets were acquired from diverse secondary data sources. Hotel Occupancy Rooms Rate was derived from BPS-Statistics Indonesia, while additional data were collected through web scraping from online travel agency websites such as Tripadvisor.com, IGT with keywords “IKN”, “hotel”, and “banjir”. For the sentiment variable from online reviews, lag effects of one, two, and three months were analyzed to determine the correlation with TPK. The highest correlation was selected for inclusion in the prediction model across all machine learning methods.
Result: The results showed that the use of IGT and online traveler reviews increased the precision of forecasting models. The best model of hotel TPK nowcasting was Random Forest Regression with the lowest MAPE value and accuracy of 5.37% and 94.63%, respectively.
Novelty: The proposed method showed great potential in improving the prediction of hotel TPK by leveraging new technology and extensive data sources. The correlation with TPK decreases with an increasing time lag of sentiment. Therefore, the sentiment of reviews in the current month has the highest correlation with TPK, compared to the previous one, two, or three months.