Optimization of Financial Asset Allocation and Risk Management Strategies Combining Internet of Things and Clustering Algorithms
Bibliographic record
Abstract
This study proposes a new method for optimizing household financial asset allocation (FAA) and developing scientific risk control strategies by integrating Internet of Things (IoT) data and clustering algorithms. IoT technology is utilized to collect real-time data, including macroeconomic indicators, market dynamics, and investor behavior. The data comes from national statistical offices, financial market trading platforms, and social media. The optimized K-means++ clustering algorithm is used for asset classification. Moreover, its performance is evaluated through indexes, such as the silhouette coefficient, adjusted rand index (ARI), Davies–Bouldin index (DBI), and mutual information (MI). The results show that the K-means++ algorithm outperforms these indexes, especially in terms of silhouette coefficient (0.62), ARI (0.75), and MI (0.80). In terms of asset allocation optimization, the proportion of stock products and wealth management products has increased to 4.94% and 12.34%, indicating an improvement in asset diversification and risk diversification. Risk assessment reveals that Internet financial behavior and economic development level have a marked impact on asset allocation. For example, the asset allocation of households with active Internet financial behavior is more diversified. The cash deposit ratio in the eastern region is 79.32%, lower than the 86.08% in the western region. This study provides effective methods for managing household financial assets, which can help improve household wealth management, enhance risk management capabilities, and promote the development of financial technology.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".