International Journal for Applied Information Management

Predicting Smartphone Prices Based on Key Features Using Random Forest and Gradient Boosting Algorithms in a Data Mining Framework

Retno Wahyusari, Nur Azizah — Tue, 01 Jul 2025 00:00:00 +0000

This study aims to predict smartphone prices using machine learning models, specifically Random Forest and Gradient Boosting algorithms, based on various smartphone features such as internal memory, RAM, processor speed, battery capacity, and camera specifications. The dataset, consisting of 980 smartphones available in India, was preprocessed to handle missing values and categorical variables, ensuring it was ready for model training. The models were evaluated using Mean Squared Error (MSE) and R-squared (R²) scores, with Gradient Boosting outperforming Random Forest in terms of predictive accuracy. Key findings from the feature importance analysis revealed that internal memory, RAM, and processor speed were the most influential features in determining smartphone prices. The results indicate that machine learning models, particularly tree-based algorithms, are effective tools for predicting smartphone prices based on hardware specifications. This study has practical implications for businesses and consumers, as it provides insights into the factors influencing smartphone prices, helping businesses optimize pricing strategies and assisting consumers in making more informed purchasing decisions. Future research could explore deep learning models and incorporate additional features, such as market demand and consumer sentiment, to improve prediction accuracy.

Predicting Pharmaceutical Product Discontinuation Using Decision Tree and Random Forest Algorithms Based on Product Attributes

Susilo Suhartono, Zahara Nabila — Tue, 01 Jul 2025 00:00:00 +0000

This study aims to predict the discontinuation of pharmaceutical products using machine learning models, focusing on key product attributes such as manufacturer, composition, price, and packaging. A comprehensive dataset of over 250,000 pharmaceutical products from India was analyzed, with two models—Decision Tree and Random Forest—being employed for prediction. The models were evaluated based on accuracy, precision, recall, and F1-score. The Random Forest model outperformed the Decision Tree with a higher accuracy, but both models struggled with the imbalanced dataset, showing low recall for the minority class (discontinued products). Feature importance analysis identified manufacturer and composition as the most influential factors in predicting product discontinuation. These findings offer valuable insights for pharmaceutical companies in managing product portfolios and optimizing their lifecycle strategies. Despite limitations in data quality and class imbalance, this study provides a foundation for future research, suggesting the integration of additional data sources and the application of deep learning techniques to further enhance prediction accuracy.

Clustering Netflix Shows Based on Features Using K-means and Hierarchical Algorithms to Identify Content Patterns

B Herawan Hayadi, Eko Priyanto — Tue, 01 Jul 2025 00:00:00 +0000

This study explores clustering patterns within Netflix's movie catalog by applying K-means and hierarchical clustering algorithms. The primary objective is to identify distinct content groups based on features such as movie duration, release year, and content ratings. The dataset, which includes 5,185 Movies, was preprocessed by handling missing values, one-hot encoding categorical variables, and standardizing numerical features. Four distinct clusters were identified, with each cluster exhibiting unique characteristics. Cluster 0 primarily consists of longer, family-friendly Movies rated TV-14, while Cluster 1 contains shorter, mature Movies with a TV-MA rating. Cluster 2 represents a diverse range of TV-MA Movies with moderate durations, and Cluster 3 focuses on adult-oriented, longer Movies with an 'R' rating. These findings offer valuable insights into Netflix's content strategy, highlighting the platform's ability to cater to different audience segments based on content type and viewer preferences. The results suggest that Netflix can leverage clustering patterns to improve its recommendation system and content acquisition strategy. However, the study is limited by the absence of user-specific data and the reliance on basic metadata features. Future research could explore the integration of additional features like user ratings and apply deep learning techniques for more sophisticated clustering.

Analyzing Customer Spending Based on Transactional Data Using the Random Forest Algorithm

Quba Siddique, Arif Muamar Wahid — Thu, 01 May 2025 00:00:00 +0000

This study explores customer spending behavior using transactional data from a retail dataset, employing a Random Forest Regressor to predict the total amount spent by customers. The dataset includes various customer attributes such as age, gender, and product category, alongside transactional details including quantity purchased and price per unit. Through Exploratory Data Analysis (EDA), it was found that Price and Quantity were the most significant factors influencing total spending, with other features like Age, Gender, and Product Category playing a minimal role in predicting spending behavior. The model achieved perfect accuracy, with an R-squared value of 1.000, indicating that it explained all the variance in customer spending. The findings suggest that transactional features, particularly Price and Quantity, are the key drivers of customer spending, and retailers can optimize their marketing and sales strategies by focusing on these factors. This study also highlights the importance of data preprocessing and feature engineering in enhancing model performance, though the results were limited by the lack of external and behavioral features. Future research could further explore the impact of customer loyalty, external factors, and more complex algorithms to improve predictive accuracy.

Clustering Sleep Patterns and Health Metrics Using K-Means Algorithm to Identify Profiles of Sleep Quality and Well-being in a Diverse Population

Abednego Septiadi, Muhamad Awiet Wiedanto Prasetyo — Tue, 01 Jul 2025 00:00:00 +0000

Sleep quality is a critical element of overall health that has garnered significant attention in recent years, particularly regarding its severe impacts on both physical and mental well-being. A growing body of research underscores that insufficient or poor-quality sleep is associated with various adverse health outcomes, ranging from cognitive impairments to chronic diseases. Studies have demonstrated that the duration and quality of sleep are intricately linked to physical, social, and emotional health outcomes among various populations, including adults and children (Lallukka et al., 2018). The crucial role sleep plays in regulating both physiological and psychological processes makes it an indispensable component of health maintenance. Research indicates that sleep disturbances can impede cognitive development in children, with implications for their growth and emotional regulation (Purwanti et al., 2024). For instance, infants who achieve a higher quality of sleep demonstrate improved cognitive abilities, which can lead to better academic performance and emotional health throughout their lives (Purwanti et al., 2024). These findings suggest that interventions designed to enhance sleep quality during infancy could yield substantial long-term health benefits. Furthermore, comparable patterns have been observed in adults, where good sleep quality significantly influences psychological factors such as emotion regulation and overall mental health (Scott et al., 2021).

The psychological ramifications of poor sleep quality extend beyond mere cognitive performance. Poor sleep has been linked to increased rates of anxiety, depression, and other mood disorders (Becerra et al., 2022). A meta-analysis revealed that improving sleep quality could ameliorate the symptoms of these mental health conditions (Scott et al., 2021). Moreover, chronic sleep deprivation has been identified as a precursor to substance use disorders, suggesting a complex interplay between sleep, addiction, and mental health (Freeman & Gottfredson, 2018). The challenges of maintaining sleep quality have been exacerbated by external stressors such as the COVID-19 pandemic, leading to increased anxiety and altered sleep patterns among various demographics, particularly students and healthcare workers (Fan et al., 2021). Physical health is equally affected by sleep quality. Quality sleep is pivotal for metabolic regulation, immune function, and recovery from injuries. Poor sleep has been associated with a range of chronic health issues, including obesity, diabetes, and cardiovascular diseases (Du et al., 2021). For instance, individuals who experience poor sleep tend to exhibit higher dietary risks and poor lifestyle choices, leading to serious health complications (Du et al., 2021). The immunological impacts of sleep deprivation further elucidate its role in health, indicating that compromised sleep can weaken the immune system and elevate susceptibility to viral infections such as COVID-19 (Pillay et al., 2020).