Articles

Stock Price Forecasting on Time Series Data Using the Long Short-Term Memory (LSTM) Model

/0 Comments/in /by

Stock price forecasting on time series data is a complex task due to the dynamic and uncertain nature of financial markets. This research aims to forecast stock prices by applying an advanced machine learning model, namely Long Short-Term Memory (LSTM), a deep learning architecture that excels in capturing long-term dependencies in time series data. The dataset used in this study consists of 1221 daily ANTM.JK stock price data over the period April 30, 2019 to April 30, 2024. The model was trained and evaluated using performance metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) in measuring the level of forecasting accuracy. The results show that the LSTM model can accurately predict stock prices on time series data, as evidenced by the MAPE accuracy evaluation value of 2.52% and RMSE of 54.64. These findings indicate that the LSTM model is effective in predicting stock prices on time series data and can be used as a supporting tool in making the right investment decisions.

Study Case: Company Valuation and Forecasting Financial Trends at PT PP London Sumatera Indonesia (LSIP)

/in /by

PT PP London Sumatra Indonesia Tbk (LSIP) is a company that has been established in Indonesia since 1906 and started its IPO in 1996 with an IPO price of Rp4.650 for each share. Even though the company’s performance is going well and the trend of palm oil consumption in Indonesia is increasing, the share price of PT PP London Sumatra Indonesia Tbk has fluctuated and even decreased when compared to the initial IPO price and share prices in the last 5 years. So this raises the question of how the company’s stock performance will be in the next few years. In this research, the author begins by analyzing the macro-environment which may have an impact on the company and industry, then the author carries out an analysis of the financial statements of the company and its competitors. Apart from that, the author also tries to forecast the company’s financial performance and then continue with company valuation analysis using the discounted cash flow method. After getting the valuation results, the author tries to see the company’s level of sensitivity using scenario analysis and also carries out capital structure analysis to find the optimal capital structure. Based on the results of financial performance analysis, Lonsum (LSIP) has better financial performance compared to its competitors except for assets turnover. And then based on the results of discounted cash flow analysis, this company is not yet worthy of being a place for us to invest. And the last based on all the results of the previous analysis, when compared with competing companies, LSIP is a company that has quite a lot of potential as a place to invest. However, currently the company still has to look for a catalyst in order to become a company that is worthy of being a place for us to invest.  Based on the result, the author suggest the reader to continue to collect information related to PT PP London Sumatra Indonesia Tbk, other competitors and plantation in similar industries to find catalysts that have positive impact on the company, and invest when the company has a positive catalyst.

Predictive Analysis for Inventory Management of Coconut Warehouse (Case Study: Banio Lahewa)

/in /by

Inventory management plays a pivotal role in the coconut farming business, directly influencing sales and income. An essential component of this management is warehousing, which not only affect revenue but also involves suppliers in the coconut storage process. Warehousing management and technology are two elements that can help companies operate more effectively and efficiently. This research focuses on efforts to improve warehouse management efficiency in the agricultural sector, particularly at Banio Lahewa, a company that operates as a coconut supplier in a small village with limited resources. Currently, the company still records data manually and lacks a real-time system to monitor demand patterns, stock rotation, and restocking frequency in the warehouse. This situation is caused by uncertainty about the products entering the warehouse, leading to the company’s focus being more limited to daily operational issues rather than future planning. To address this challenge, this research uses future event prediction methods, specifically forecasting by applying two neural network models: the Feed Forward Neural Network and the Long Short Term Memory. The implementation of this system is expected to provide new insights to the company, enabling them to be more adaptive in efficiently managing warehouse systems. With an understanding of patterns and predictions of future events, it is expected that the company can be more prepared and responsive to changes in customer demand and able to expand products more quickly. The results of this research are expected to make a positive contribution to the company, helping them optimize warehouse management and become more adaptive to market dynamics.

Forecasting the Demand of Honey Product for Facing Panic Buying and Stockpile in Pandemics

/in /by

The threat on health sector has massive impacts, and one of them is on business internal management as the main factor of producers to consider design of their products. During pandemic, honey is categorized as food supplement. In a certain phase, when the demand upon honey is high, the price tends to be unstable due to an imbalance between supply and demand. Complexities of consumer during pandemics effect on food security system. Unpreparedness of the producers in facing the phenomenon of panic buying and stockpile causes scarcity. Objective of the research was forecasting the demand of honey following the second pandemic wave and supported SMEs to create adaptive strategy to face scarcity. Method of the research used secondary data and survey in the field, which was ended by FGD to decide strategy of the producer to minimize scarcity. Data analysis used MSE (Mean Squared Error) with exponential smoothing. Results of the research showed that the method of alpha exponential 5% has minimum error, which forecast that in December 2021, the demand of propolis honey may reduce after the 2nd wave of Covid in Indonesia and approach to normal forecasting system. The accuracy with exponential method is higher and may facilitate the producers to provide products when fear contagion and panic buying take place. Contribution of analysis result toward strategy of the producers is providing estimation that maximum amount of availability increases no more than 2 times of the real demand of the consumers when panic buying occurs. The most needed strategy is setting the timeline in the projection of consumer journey. This alternative is relevant to fear contagion phenomenon because it contributes to socio-psychology of the consumers in deciding to buy supplement of honey product. Novelty of this research is examining the frequency wave of product purchase intensity of the consumer journey with Covid-19 phenomenon.