CoChat
Sign Up
Cited by 13Decision Support System ApplicationsFuzzy Logic and Control SystemsRecommender Systems and Techniques

Adaptive neuro-fuzzy inference system for customizing investment type based on the potential investors’ demographics and feedback

Open access
Asemi, Asefeh, Asemi, Adeleh, Ko, Andrea·2023·Journal of Big Data
DOI 10.1186/s40537-023-00784-7
Open this paper in CoChat — free accountOpen PDF

Abstract

The proposed model is an adaptive neuro-fuzzy inference recommender system that utilizes customer investment service feedback and fuzzy neural inference solutions to generate personalized investment recommendations. The model is designed to support the investment process for the customers and takes into consideration seven factors to implement the proposed investment system model through the customer or potential investor data set. These include demographic data and investment type. The model is divided into three main phases: data gathering, data analysis, and decision-making. In the data gathering phase, initial data is collected through a web-based platform, and in the data analysis phase, the potential investors' demographic criteria are extracted and grouped, and the types of investments are then clustered. The output obtained is transferred to the ANFIS layer, and investment-type recommendations are extracted for each group of potential investors. Investor feedback is received to improve and develop the system. JMP and MATLAB are used to propose the model, which serves as a framework for investment recommender systems. It demonstrates how to use this framework to offer pertinent and precise recommendations for the best sort of investment type to potential and present investors by combining the expertise of the experts and the demographic information of potential investors. Overall, this paper provides a new, novel model for investment recommender systems, which can assist investment companies, individual investors, and fund managers in their investment decisions.

AI snapshot

Written from the paper’s full text.

TL;DR

The paper proposes an ANFIS-based investment recommender system that uses six demographic inputs and investor feedback to recommend investment types, with investment types clustered into three groups via K-means in JMP and modeled in MATLAB. It reports a DemographicANFIS with 1296 fuzzy rules and an average testing error of 0.86683 on 1542 survey responses.

Key findings

  • K-means clustered investment types into three clusters: cluster 1 had 592 respondents, cluster 2 had 406, and cluster 3 had 340. Cluster 1 was ranked top and included government securities, mutual funds, and listed stock/equity; cluster 2 included listed stock/equity, mutual funds, voluntary pension funds, and government securities; cluster 3 included listed stock/equity, voluntary pension funds, and government securities.
  • The DemographicANFIS used six demographic inputs (gender, age, location, education, job, income) and one output (investment-type clusters). It generated 1296 fuzzy rules, used 1542 training data pairs, and contained 2647 nodes with 1365 parameters (1296 linear and 69 non-linear).
  • Training used a hybrid method with 3 epochs; epoch 3 error was 0.8668, and the average testing error was 0.86683.
  • The paper reports example relationships from the ANFIS graphs, such as income and gender/age/location/job/education combinations mapping to different investment-type clusters.

Methods

  • The study used quantitative and qualitative methods. Data came from an online Portfolio Investment Questionnaire conducted in Hungarian in 2019, with 1542 responses; the data were translated into English, cleaned, and prepared for analysis. Investment-type questions included P24–P27.
  • Investment types were clustered in JMP using K-means, with elbow curves and silhouette scores used to determine the optimal number of clusters; missing values were removed before clustering.
  • The ANFIS was implemented in MATLAB R2022b using a Sugeno-type fuzzy inference system, with six demographic inputs and three investment-type clusters as output. A hybrid learning method was used with 3 epochs and error tolerance 0; expert knowledge and investor feedback were used to add, modify, or remove rules.

Limitations

  • The paper states that the system only considers potential investors’ demographic information, that inputs are limited to six variables, and that only a few investment types are clustered as output. It also notes that rules will change if investor characteristics or investment types change, and recommends future work on other traits and intelligently generated knowledge-based rules.
  • The paper states that users should test the system in real-world settings and that new fuzzy rules can be generated from feedback.
  • Evident from the text: Table 3 frequencies do not sum to the stated 1542 responses, and some categories are very small (e.g., income above 350,000 HUF n=7; age 55–79 n=100). The three cluster counts also sum to 1338, not 1542, which raises questions about data consistency and robustness.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s40537-023-00784-7

Cites

27 of 28 references verified1 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 3 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    The first cluster of investment types includes potential investors with postgraduate degrees and lower manager jobs.

    “the first cluster of investment types includes potential investors with postgraduate degrees and lower manager jobs”
    Quote in the paperNot a substantial claim
  • Findingown data

    Potential investors with monthly incomes of more than 500,000 forints are primarily in the third type of investment cluster.

    “and those with monthly incomes of more than 500,000 forints primarily in the third type of investment cluster.”
    Quote in the paperNot a substantial claim
  • Findingown data

    The third cluster includes 340 respondents.

    “The third cluster, with 340 respondents, is in third place.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Potential investors living in Budapest and earning less than HUF 100,000 per month belong to the third investment type cluster.

    “potential investors living in Budapest and earning less than HUF 100,000 per month belong to the third investment type cluster”
    Quote in the paperNot a substantial claim
  • Findingown data

    The K-Means clustering of investment types produced three clusters with counts of 592, 406, and 340 for the first, second, and third clusters respectively.

    “The first cluster has a count of 592, the second has a count of 406, and the third has a count of 340, according to the cluster summary.”
    Quote in the paperNot a substantial claim
  • Classified as probably not a substantial claim. 28
  • May combine two claims. 9

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingown data

    The DemographicANFIS system achieved a training error of 0.8668 at epoch 3.

    “Epoch 3: error = 0.8668.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingnone given

    The system consists of 1365 parameters, with 1296 linear and 69 non-linear.

    “This system consists of a total of 1365 parameters, with 1296 being linear and 69 non-linear.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Potential investors in the third cluster of investment type have a middle manager job and make less than 100,000 forints per month.

    “potential investors in the third cluster of investment type have a middle manager job and make less than 100,000 forints per month.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Individuals in the second cluster have invested in the stock market within the last 3 years and regularly kept an eye on and followed the stock's performance.

    “These individuals have invested in the stock market within the last 3 years and regularly kept an eye on and followed the stock's performance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingown data

    The DemographicANFIS investment recommender system was created using 2647 nodes.

    “The results show that a DemographicANFIS investment recommender system was created using 2647 nodes.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Findingnone given

    As system inputs, these data are also constrained to six variables.

    “As system inputs, these data are also constrained to six variables.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Individuals in the third cluster made an investment in the stock market in the previous 3 years and regularly checked in on and followed the stock's performance.

    “These individuals made an investment in the stock market in the previous 3 years and regularly checked in on and followed the stock's performance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingnone given

    The output of the ANFIS system corresponds to three clusters of investment types.

    “The output of the ANFIS system, which corresponds to three clusters of investment types, is referred to as a factor.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingnone given

    Machine learning techniques generated 1542 training data pairs for the system.

    “Machine learning techniques were utilized to generate 1542 training data pairs for the system.”
    • Also stated in: § Proposition of demographicanfis · plain
      “Additionally, 1542 train data pairs are taken into consideration.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Individuals in the first cluster have not made any stock market investments in the previous 3 years and did not regularly monitor or follow the stock's performance.

    “These individuals have not made any stock market investments in the previous 3 years and did not regularly monitor or follow the stock's performance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The proposed model considers seven factors, including demographic data and investment type, from customer or potential investor data.

    “The model is designed to support the investment process for the customers and takes into consideration seven factors to implement the proposed investment system model through the customer or potential investor data set.These include demographic data and investment type.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationnone given

    The proposed model is an adaptive neuro-fuzzy inference recommender system that uses customer investment service feedback and fuzzy neural inference to generate personalized investment recommendations.

    “The proposed model is an adaptive neuro-fuzzy inference recommender system that utilizes customer investment service feedback and fuzzy neural inference solutions to generate personalized investment recommendations.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    This ANFIS-based investment recommender system evaluates the potential investor's demographic information and, using a combination of professional judgments, suggests which investment type is best for each customer demographic.

    “This ANFIS-based investment recommender system evaluates the potential investor's demographic information and, using a combination of professional judgments, suggests which investment type is best for each customer demographic.”
    Quote in the paperNot a substantial claim
    • Rests on an assumption: Potential investors have various investment requirements depending on their demographics, and therefore select various forms of investments.
    • Rests on an assumption: Demographics and financial attitudes are related and influence the choice of investment type or product.
    • Rests on an assumption: Demographic factors can provide valuable insight into how investors and potential investors use and evaluate the company's services and products, and can help predict the behavior of current and potential customers.
    • Rests on an assumption: Expert knowledge can enhance the system and add rules that improve the system.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The authors have considered a more comprehensive set of factors, including demographic data which can influence the investor's decision-making process and make the recommendations more personalized.

    “Additionally, the authors have considered a more comprehensive set of factors, including demographic data which can influence the investor's decision-making process and make the recommendations more personalized.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Interpretationnone given

    Two categories of new rules for the proposed investment recommender system are defined by investment experts using their knowledge.

    “What matters is that two categories of new rules for the proposed investment recommender system are defined by investment experts using their knowledge.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    The paper provides a new, novel model for investment recommender systems.

    “Overall, this paper provides a new, novel model for investment recommender systems, which can assist investment companies, individual investors, and fund managers in their investment decisions.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    These clusters of investment types can be used to guide potential investors in selecting investment products such as government securities, mutual funds, stocks/shares on stock exchanges, and voluntary pension funds.

    “These clusters of investment types can be used to guide potential investors in selecting investment products such as government securities, mutual funds, stocks/ shares on stock exchanges, and voluntary pension funds.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The study proposes a novel business model for an investment recommender system that utilizes ANFIS to suggest the appropriate type of investment based on demographic data collected from potential investors.

    “In order to address this issue, this study proposes a novel business model for an investment recommender system that utilizes adaptive neural fuzzy inference (ANFIS) to suggest the appropriate type of investment based on the demographic data collected from potential investors.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Potential investors have various investment requirements depending on their demographics, and therefore select various forms of investments.
    • Rests on an assumption: Demographics and financial attitudes are related and influence the choice of investment type or product.
    • Rests on an assumption: Demographic factors can provide valuable insight into how investors and potential investors use and evaluate the company's services and products, and can help predict the behavior of current and potential customers.

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationreasoning

    This study fills the gap in the literature that few studies have used the ANFIS technique and demographic information to recommend the investment types.

    “Therefore, it fills the gap in the literature that few studies have used the ANFIS technique and demographic information to recommend the investment types.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    This study makes a valuable contribution to the field by providing a new and innovative approach to the problem of investment recommendations.

    “Overall, this study makes a valuable contribution to the field by providing a new and innovative approach to the problem of investment recommendations.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Premisecitation

    Recommender systems should be tailored to meet the specific needs of clients.

    “This is particularly important as Kanaujia and his colleagues have highlighted that recommender systems should be tailored to meet the specific needs of clients [17].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [17] Kanaujia PKM, Manjusha P, Siddharth SR. A framework for development of recommender system for financial data analysis. Int J Inform Eng Electron Bus. 2017;9(5):18–27.

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    Not all the rules that can be created based on the available variables are necessarily generated by the proposed investment recommender system.

    “Not all the rules that can be created based on the available variables are necessarily generated by the proposed investment recommender system.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    The ANFIS system categorizes customers based on six demographic traits using six input factors.

    “The ANFIS system categorizes customers based on six demographic traits using six input factors.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    This study differs from previous studies in its focus on utilizing demographic information and investment preferences to generate personalized recommendations for potential investors and making use of the ANFIS system for grouping and analyzing data.

    “However, this study differs in its focus on utilizing demographic information and investment preferences to generate personalized recommendations for potential investors and making use of the ANFIS system for grouping and analyzing data.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationown data

    Based on comments made by investors using the system, it is possible to put expert judgments into practice.

    “Based on comments made by investors using the system, it is also possible to put expert judgments into practice.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationnone given

    The system is built on a novel, intelligent methodology that makes use of ANFIS and six demographic factors.

    “The system is built on a novel, intelligent methodology that makes use of ANFIS and six demographic factors.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    An expert can modify one or more of the six variables in each rule the system generates and produce a new rule.

    “As a result, the expert can modify one or more of the six variables in each rule the system generates and produce a new rule.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Interpretationnone given

    The model's initial inputs are gathered from regular users who are thought of as potential investors.

    “that the model's initial inputs are gathered from regular users who are thought of as potential investors.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    The rules produced by the system will alter as the characteristics of potential investors are changed as inputs and as investment types are altered as an output of the system.

    “Naturally, the rules produced by the system will alter as the characteristics of potential investors are changed as inputs and as investment types are altered as an output of the system.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Jung first presented ANFIS in 1993, and its primary benefit is how it simplifies the establishment of logical judgment.

    “Jung first presented this system in 1993 (Jung, 1993), and its primary benefit is how it simplifies the establishment of logical judgment [3].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites Jung, 1993

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

    • cites [3] Asemi A, Asemi A. Intelligent MCDM method for supplier selection under fuzzy environment. Int J Inf Sci Manag (IJISM). 2014;12(2):33–40.

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    The authors use the ANFIS system, which is a combination of the neural network and fuzzy logic, to group and analyze data which is something that the previous papers have not proposed.

    “Moreover, the authors use the ANFIS system, which is a combination of the neural network and fuzzy logic, to group and analyze data which is something that the previous papers have not proposed.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    The system attempts to address the issue of incomplete or inaccurate data by using the function described for it.

    “This system attempts to address the issue of incomplete or inaccurate data by using the function described for it.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Interpretationnone given

    Another drawback is that only a few investment types are clustered together and viewed as the system's output.

    “Another drawback is that only a few investment types are clustered together and viewed as the system's output.”
    Quote in the paperSubstantial claim
33 of 33

  • The paper relies on this without support.

    Potential investors have various investment requirements depending on their demographics, and therefore select various forms of investments.

    “Potential investors have various investment requirements depending on their demographics.As a result, they select various forms of investments.”

  • The paper relies on this without support.

    Income, savings, and employment may be the most crucial criteria in selecting the sort of investment.

    “For instance, the most crucial criteria in selecting the sort of investment may be income, savings, and employment.”

  • The paper relies on this without support.

    Demographics and financial attitudes are related and influence the choice of investment type or product.

    “Their responses help us better understand how demographics and financial attitudes are related, and ultimately how these factors influence the choice of investment type/product.”

  • The paper relies on this without support.

    Demographic factors can provide valuable insight into how investors and potential investors use and evaluate the company's services and products, and can help predict the behavior of current and potential customers.

    “Factors such as age, gender, occupation, educational attainment, field of study, domicile, place of employment, and other pertinent personal data can provide valuable insight into how investors and potential investors use and evaluate the company's services and products.This understanding can also help predict the behavior of current and potential customers.”

  • The paper relies on this without support.

    Expert knowledge can enhance the system and add rules that improve the system.

    “The input of investment experts and their specialized knowledge is used to enhance the system and add rules.”

  • The paper relies on this without support.

    Demographic factors (gender, age, location, education, job, income) are sufficient to determine an individual's investment type preferences.

    “The ANFIS system categorizes customers based on six demographic traits using six input factors.”

  • The paper relies on this without support.

    The three clusters of investment types derived from the data are meaningful and correspond to distinct investment preferences.

    “The output of the ANFIS system, which corresponds to three clusters of investment types, is referred to as a factor.”

  • The paper relies on this without support.

    Expert knowledge can be effectively incorporated as fuzzy rules to improve the system.

    “This implies that investment experts can add rules to this system in addition to those that are intelligently generated by it.”

  • The paper relies on this without support.

    Investor feedback can improve the system.

    “Investors and experts both provide feedback, and the system can be improved as a result.”

  • The paper relies on this without support.

    The ANFIS model with chosen parameters (Gaussian MFs, hybrid learning, 3 epochs) is appropriate for this problem.

    “The FIS training method is a hybrid with three epochs.”

  • The paper relies on this without support.

    The training and testing errors (0.8668, 0.86683) indicate acceptable performance.

    “Epoch 3: error = 0.8668.”

  • The paper relies on this without support.

    The proposed system can operate based on erroneous or incomplete data.

    “The proposed system's ability to operate based on erroneous or incomplete data is another innovation.”

  • The paper relies on this without support.

    A new rule that incorporates all the variables and is not currently generated by the system can be added to it based on feedback from investors who use the system and the opinions of experts.

    “Consequently, a new rule that incorporates all the variables and is not currently generated by the system can be added to it based on feedback from investors who use the system and the opinions of experts.”
13 of 13

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Kovács, Ko, and Asemi are cited under the wrong reference number

    Minor

    The literature review cites Kovacs, Ko, and Asemi as reference [4], but the reference list assigns their paper number 18; reference 4 is by Asemi and Ko.

  • ANFIS input and membership-function counts conflict

    Minor

    The paper describes the financial ANFIS as having four inputs with three membership functions each, but describes the implemented DemographicANFIS as having six inputs whose membership-function counts vary from two to nine.

2 of 2

Cites

Flagged first, then by citations

Research works printed but not linked: 4

  1. Alpaydin, E. (2020). Introduction to Machine Learning (Fourth ed.). MIT. pp. xix, 1–3, 13–18. ISBN 978–0262043793.
  2. Asemi A, Asemi A. Intelligent MCDM method for supplier selection under fuzzy environment. Int J Inf Sci Manag (IJISM). 2014;12(2):33–40.
  3. Burke R. Hybrid web recommender systems. In: Brusilovsky P, Kobsa A, Nejdl W, editors. The Adaptive Web. Berlin/Heidelberg: Springer; 2007.
  4. Faridniya A, Faridnia M. Providing a model for allocating resources and choosing investment type using Data Envelopment Analysis (DEA) (Case Study: Social Security Organization). J Adv Pharm Edu Res. 2019;9(S2):112–24.

Cited by

Sorted by citations

Related

Authors
Asemi, A., Asemi, A., & Ko, A.
Venue
Journal of Big Data
Publisher
Springer Science and Business Media LLC
Published
2023-05-28
Volume
10
Issue
1
ISSN
2196-1115 (ISSN-L)
DOI
10.1186/s40537-023-00784-7
OpenAlex
W4378594041
Semantic Scholar
d98d325e7f63359d6c8068731b0bb6b15610958a
Cited by
13
References
23
Citations by year
2026: 3 · 2025: 4 · 2024: 5 · 2023: 1
FWCI
3.74
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal Of Big Data (publishedVersion, cc-by)
  • Corvinus Research Archive (Corvinus University of Budapest) (acceptedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Corvinus University of Budapest
Topics
  • Social Sciences › Business, Management and Accounting › Management Information Systems › Decision Support System Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Fuzzy Logic and Control Systems
  • Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
Keywords
adaptive neuro-fuzzy inference system, investor demographics, customer feedback, investment decision support, expert knowledge integration

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-29.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-29.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review