IJSSER

Title: PREDICTIVE MODELLING TECHNIQUES AND APPLICATIONS
Authors: Saanvi Arora
\|\| \|\|
Saanvi Arora Delhi Public School
MLA 8 Arora, Saanvi. "PREDICTIVE MODELLING TECHNIQUES AND APPLICATIONS." Int. j. of Social Science and Economic Research, vol. 6, no. 12, Dec. 2021, pp. 4830-4836, doi.org/10.46609/IJSSER.2021.v06i11.024. Accessed Dec. 2021. APA 6 Arora, S. (2021, December). PREDICTIVE MODELLING TECHNIQUES AND APPLICATIONS. Int. j. of Social Science and Economic Research, 6(12), 4830-4836. Retrieved from doi.org/10.46609/IJSSER.2021.v06i11.024 Chicago Arora, Saanvi. "PREDICTIVE MODELLING TECHNIQUES AND APPLICATIONS." Int. j. of Social Science and Economic Research 6, no. 12 (December 2021), 4830-4836. Accessed December, 2021. doi.org/10.46609/IJSSER.2021.v06i11.024.
References [1]. Ali, R, (2020), ‘Predictive Modeling: Types, Benefits, and Algorithms’, Netsuite, https://www.netsuite.com/portal/resource/articles/financial-management/predictive-modeling.shtml#target7 [2]. Bari, A, (n.d), ‘How Predictive Analysis Neural Networks Work’, Dummies, https://www.dummies.com/programming/big-data/data-science/how-predictive-analysis-neural-networks-work/ [3]. Brown, A, (2021), ‘Understanding The Technical And Societal Relationship Between Shadowbanning And Algorithmic Bias’, Forbes, https://www.forbes.com/sites/anniebrown/2021/10/27/understanding-the-technical-and-societal-relationship-between-shadowbanning-and-algorithmic-bias/?sh=2adcfccb6296 [4]. Du, M, (2020), ‘Modern Challenges of Predictive Modelling’, Medium, https://medium.com/swlh/modern-challenges-of-predictive-modelling-74c273b290b6 [5]. Fox, P, (n.d), ‘Bias in predictive algorithms’, Khan Academy, https://www.khanacademy.org/computing/ap-computer-science-principles/data-analysis-101/x2d2f703b37b450a3:machine-learning-and-bias/a/bias-in-predictive-algorithms [6]. Knowledge@Wharton, (2019), ‘Removing Human Bias from Predictive Modeling’, https://knowledge.wharton.upenn.edu/article/removing-bias-from-predictive-modeling/ [7]. Lau, T, and Akkaraju, U, (2019), ‘When Algorithms Decide Whose Voices Will Be Heard’, Harvard Business Review, https://hbr.org/2019/11/when-algorithms-decide-whose-voice-will-be-heard [8]. Omnisici, (n.d), ‘Technical Glossary: Predictive Modelling’,https://www.omnisci.com/technical-glossary/predictive-modeling [9]. Panchotia, R, ‘Predictive Modelling Using Linear Regression’, Medium,https://medium.com/swlh/predictive-modelling-using-linear-regression-e0e399dc4745 [10]. Parthasarathy, S, (2021), ‘What is Predictive Analytics?’, https://www.logianalytics.com/predictive-analytics/what-is-predictive-analytics/ [11]. SAS, (n.d), ‘Predictive Modeling Techniques’, https://www.sas.com/ko_kr/insights/analytics/predictive-modeling-techniques.html [12]. Selerity, (n.d), ‘Types of predictive analytics models and how they work’, https://seleritysas.com/blog/2019/12/12/types-of-predictive-analytics-models-and-how-they-work/ [13]. Warudkar, H, (2020), ‘Prediction using Neural Networks’, Express Analytics, https://expressanalytics.com/blog/neural-networks-prediction/
Abstract: Predictive modelling has developed rapidly in the last decade and is now used in every industry, with predictive modelling algorithms governing almost every area of life from consumer industry to healthcare and transportation. From more basic techniques, predictive modelling has evolved into more complex structures such as neural networks, increasingly using artificial intelligence and machine learning. While acknowledging the benefits and ease these techniques have brought to society and increased innovation, this paper argues that the challenges and social implications of predictive modelling cannot be ignored. Increasing concerns regarding the lack of accountability of algorithms, unintended effects on human rights and opportunities as well as privacy concerns must be addressed for predictive modelling to be harnessed in a way that is transparent and serves the well-being of the greatest number of people. This paper examines these key arenas of challenges through case studies and proposes policy interventions to improve the framework of accountability for corporations and governments which make use of predictive modelling algorithms and decrease bias in the datasets which these algorithms are trained on.

IJSSER is Member of