Conception, développement et évaluation d’un système en ligne d’aide à la décision pour le choix de produits financiers
Bibliographic record
Abstract
Small investors are confronted with multiple challenges when it comes to choosing how, with whom and where to invest. The investment process can be time consuming especially for those with basic skills and knowledge on the subject. The specific terminologies related to financial services, the immensity of products and intermediaries, the lack of experience exposing one to possible fraud and the lack of standardized methods are some examples of challenges that an investor might come across during the investment process. The purpose of this research is to develop and test an online experimental decision support system that would both mitigate the risks for small investor by increasing their level of awareness and knowledge and optimizing their decision process by presenting them a clear and complete picture of their investor profile and corresponding financial products. The system supports the investors through a structured investment process leading to a quick overview of the financial products available on the market and their characteristics. The system has a specific mission: to support the investors in their investment process through a structured decision making process that procures information on the terminology of the financial sector and on the different types of products and services corresponding their needs. The system was developed in three phases. During the analysis phase, a literature review was conducted during which we went over the 3 investments guides published by the AMF (Autorite des Marches Financiers) and the financial policies regulating the financial market in Quebec in order to define a structured investment decision making process and the critical elements to take into account when defining an investor’s profile. Documentations published by the CFA Institute (Chartered Financial Analyst Institute) and the MiFID (Markets in Financial Instruments Directive) along with multiple scholarly literatures were consulted to deepen our understanding of the financial domain and to define the parameters of the system. Financial experts were also consulted to help and guide in the development process. Then, 22 similar decision support systems from 19 different creators, both local and international, were analysed in order to benchmark their way of defining investor’s profile and the content of their systems. By the end of this phase, the functional and technical requirements of the system were defined allowing the beginning of the next phase.
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 | 0.015 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.012 | 0.007 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".