Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM58845
Volume:
10 |
4 |
April 2026
Pages:
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
The continuous expansion of the cryptocurrency market has intensified the demand for intelligent, trustworthy, and user-centric analytical platforms. Cryptosden is a comprehensive MERN-stack (MongoDB, Express.js, React, Node.js) web application engineered to overcome the shortcomings of existing cryptocurrency platforms by providing a centralized, secure, and highly informative hub for both novice and experienced users. The platform delivers dynamically updating crypto values sourced from the CoinGecko API, enabling users to monitor over 3,000 digital assets in real time across four fiat currencies — USD, INR, EUR, and GBP. Cryptosden distinguishes itself through four proprietary AI-powered modules: a composite Coin Trust Score that evaluates market health across six weighted data streams; an Emotional Volatility Index (EVI) that quantifies collective community sentiment; a Gated Recurrent Unit (GRU)- based Price Prediction Engine that forecasts coin prices over four time horizons using 13 engineered technical features; and a parallel Anomaly Detection and Whale Alert System employing Z-score statistics, Isolation Forest machine learning, and blockchain transaction monitoring. A Gemini-powered AI chatbot further assists users in interpreting complex market signals in natural language. The platform targets retail cryptocurrency participants who need consolidated analytical intelligence to make informed buy, sell, or hold decisions — without the system providing direct financial advice. This paper presents the full architecture, AI algorithms, experimental results, and comparative evaluation of Cryptosden.
KEYWORDS
Publication Date
2/3/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...