The rapid evolution of cryptocurrencies has brought transformative changes to the financial landscape. Cryptocurrency prices, characterized by their inherent volatility, pose challenges for precise forecasting. This study introduces a novel approach to cryptocurrency price forecasting, leveraging Long Short-Term Memory (LSTM) networks, known for discerning temporal dependencies within time series data. Motivated to enhance prediction accuracy, this research investigates the effectiveness of LSTM networks in capturing complexities inherent in cryptocurrency price movements. The proposed methodology involves meticulous data collection and preprocessing, utilizing an extensive dataset from Kaggle. This dataset forms the foundation for predictive modeling and facilitates an in-depth analysis of cryptocurrency price dynamics. Exploratory data analysis, including visualization techniques, and a dedicated Time Series Analysis precede the implementation of predictive models, such as LSTM networks. Results and evaluation showcase promising outcomes, emphasizing the models' precision, accuracy, and explanatory power. The Mean Absolute Error (MAE) of 0.0177 underscores the precision achieved in predicting cryptocurrency prices, while the Mean Squared Error (MSE) of 0.00066 and the R² Score of 0.9486 attest to our models' overall accuracy and explanatory power. This research significantly contributes to understanding cryptocurrency forecasting by incorporating LSTM networks, paving the way for advancements in this evolving domain.
Read MoreDoi: https://doi.org/10.54216/FinTech-I.020202
Vol. 2 Issue. 2 PP. 18-26, (2023)
The transformative impact of traditional commerce by online marketplaces is exemplified through eBay, a global platform that facilitates diverse transactions via auctions. In this research, the dynamics of eBay auctions, crucial for buyers, sellers, and researchers, are delved into. The central inquiry revolves around the key factors shaping auction outcomes, examining bid behaviors and types. The study leverages a robust dataset from eBay, meticulously curated to encompass auction identifiers, bid details, pricing information, auction types, and temporal aspects. A comprehensive approach involves data preprocessing, ensuring reliability by addressing missing values and outliers. Rigorous exploration and validation validate the dataset's integrity. Machine Learning Techniques, including MLP, SVR, Linear Regression, Extra Trees, and Gradient Boosting, form the analytical backbone. Model evaluation reveals top-performing candidates, such as MLP Regressor (0.8084), SVR (0.8210), and Linear Regression (0.8173), exhibiting superior accuracy and reliability. These models are identified for adoption in future work, emphasizing nuanced predictions in eBay auctions. This research contributes to understanding online auction dynamics, offering practical insights for eBay users and the broader e-commerce community. The models identified pave the way for enhanced predictive capabilities and continuous refinement in deciphering factors influencing auction outcomes.
Read MoreDoi: https://doi.org/10.54216/FinTech-I.020203
Vol. 2 Issue. 2 PP. 27-36, (2023)
In this work, we describe an adaptive financial management strategy, tailor-made to meet the demands of, and capitalize on, an economy ruled by AI. The suggested solution combines three essential algorithms: LSTM-based machine learning for economic forecasting; SHAP-based explainable AI for openness in decision-making; and blockchain technology with proof-of-work (PoW) security. This LSTM-based method handles the sequential data often seen in time series analysis, which is crucial for effective financial forecasting. It is particularly effective at identifying complex interrelationships in financial time series data, providing a solid basis for reliable forecasting. By giving each feature in a prediction model an equal amount of weight, the SHAP algorithm improves the openness of decisions. The experimental results confirm the superiority of the suggested technique over the conventional methods. It uses dynamic Machine Learning models, in particular LSTM networks, to provide more precise economic forecasts than static models based on averages. Using SHAP, explainable AI solves the problem of interpretability that plagues conventional techniques, allowing for more open deliberation. The combination of Blockchain with PoW gives better security, overcoming the risks of centralized systems employed in previous approaches. The suggested adaptive strategy provides a comprehensive and robust framework for managing finances in a world controlled by artificial intelligence.
Read MoreDoi: https://doi.org/10.54216/FinTech-I.020201
Vol. 2 Issue. 2 PP. 08-17, (2023)
The suggested approach, dubbed Blockchain-Enabled Secure Marketing (BESM), utilizes blockchain technology to usher in a new age in digital advertising. To solve the problems that have plagued marketing in the past, BESM combines three cutting-edge algorithms: Decentralized Identity Verification (DIVA), Consensus-Driven Targeting (CDTA), and Immutable Performance Analytics (IPAA). DIVA offers user privacy and security via decentralized identity verification, leveraging cryptographic hashes and digital signatures. CDTA revolutionizes audience selection by combining consensus-driven decision-making, encouraging accuracy and democratic involvement. IPAA protects marketing performance metrics on the blockchain, making all of the data contained within immutable and public. The results of these experiments show that BESM is superior to conventional approaches, and that it provides superior data security, user privacy, efficiency, and transparency. Algorithms as a whole strengthen the marketing ecosystem by making it more reliable and customer-focused landscapes.
Read MoreDoi: https://doi.org/10.54216/FinTech-I.020204
Vol. 2 Issue. 2 PP. 37-47, (2023)
A new age of workplace practices is about to begin, and this research delves into how HRM is undergoing a paradigm change because of analytics and solutions offered by the Internet of Things (IoT). Smart recruiting, targeted employee engagement, and ongoing performance monitoring are the main points of the suggested strategy. By using IoT devices, data is collected in real-time, allowing workers to get quick feedback and creating a work environment that is dynamic and adaptable. Decisions based on data simplify recruitment procedures, which improves talent identification and onboarding. Internet of Things (IoT) devices track employees' levels of stress and physical activity, enabling focused wellness programs. Predictive HR analytics can help with workforce planning by revealing trends that may be used for proactive decision-making. This method's innovative influence reaches into smart workplace design, which adapts to workers' evolving demands. By providing better accuracy, performance, and responsiveness than conventional HRM techniques, the suggested approach fosters an adaptive workplace that meets the changing demands of both people and the company.
Read MoreDoi: https://doi.org/10.54216/FinTech-I.020205
Vol. 2 Issue. 2 PP. 48-56, (2023)
