Search results

Good quality input data is critical to developing a robust machine learning model for identifying possible money laundering transactions. McKinsey, during one of the conferences of ACAMS, attributed data quality as one of the reasons for struggling artificial intelligence use cases in compliance to data. There were often use concerns raised on data quality of predictors such as wrong transaction codes, industry classification, etc. However, there has not been much discussion on the most critical variable of machine learning, the definition of an event, i.e. the date on which the suspicious activity reports (SAR) is filed.

The team analyzed the transaction behavior of four major banks spread across Asia and Europe. Based on the findings, the team created a synthetic database comprising 2,000 SAR customers mimicking the time of investigation and case closure. In this paper, the authors focused on one very specific area of data quality, the definition of an event, i.e. the SAR/suspicious transaction report.

The analysis of few of the banks in Asia and Europe suggests that this itself can improve the effectiveness of model and reduce the prediction span, i.e. the time lag between money laundering transaction done and prediction of money laundering as an alert for investigation

The analysis was done with existing experience of all situations where the time duration between alert and case closure is high (anywhere between 15 days till 10 months). Team could not quantify the impact of this finding due to lack of such actual case observed so far.

The key finding from paper suggests that the money launderers typically either increase their level of activity or reduce their activity in the recent quarter. This is not true in terms of real behavior. They typically show a spike in activity through various means during money laundering. This in turn impacts the quality of insights that the model should be trained on. The authors believe that once the financial institutions start speeding up investigations on high risk cases, the scatter plot of SAR behavior will change significantly and will lead to better capture of money laundering behavior and a faster and more precise “catch” rate.

Recently, disruptive technologies (DTs) have proposed several innovative applications in managing logistics and promise to transform the entire logistics sector drastically. Often, this transformation is not successful due to the existence of adoption barriers to DTs. This study aims to identify the significant barriers that impede the successful adoption of DTs in the logistics sector and examine the interrelationships amongst them.

Initially, 12 critical barriers were identified through an extensive literature review on disruptive logistics management, and the barriers were screened to ten relevant barriers with the help of Fuzzy Delphi Method (FDM). Further, an Interpretive Structural Modelling (ISM) approach was built with the inputs from logistics experts working in the various departments of warehouses, inventory control, transportation, freight management and customer service management. ISM approach was then used to generate and examine the interrelationships amongst the critical barriers. Matrics d’Impacts Croises-Multiplication Applique a Classement (MICMAC) analysed the barriers based on the barriers' driving and dependence power.

Results from the ISM-based technique reveal that the lack of top management support (B6) was a critical barrier that can influence the adoption of DTs. Other significant barriers, such as legal and regulatory frameworks (B1), infrastructure (B3) and resistance to change (B2), were identified as the driving barriers, and industries need to pay more attention to them for the successful adoption of DTs in logistics. The MICMAC analysis shows that the legal and regulatory framework and lack of top management support have the highest driving powers. In contrast, lack of trust, reliability and privacy/security emerge as barriers with high dependence powers.

The authors' study has several implications in the light of DT substitution. First, this study successfully analyses the seven DTs using Adner and Kapoor's framework (2016a, b) and the Theory of Disruptive Innovation (Christensen, 1997; Christensen et al., 2011) based on the two parameters as follows: emergence challenge of new technology and extension opportunity of old technology. Second, this study categorises these seven DTs into four quadrants from the framework. Third, this study proposes the recommended paths that DTs might want to follow to be adopted quickly.

The authors' study has several managerial implications in light of the adoption of DTs. First, the authors' study identified no autonomous barriers to adopting DTs. Second, other barriers belonging to any lower level of the ISM model can influence the dependent barriers. Third, the linkage barriers are unstable, and any preventive action involving linkage barriers would subsequently affect linkage barriers and other barriers. Fourth, the independent barriers have high influencing powers over other barriers.

The contributions of this study are four-fold. First, the study identifies the different DTs in the logistics sector. Second, the study applies the theory of disruptive innovations and the ecosystems framework to rationalise the choice of these seven DTs. Third, the study identifies and critically assesses the barriers to the successful adoption of these DTs through a strategic evaluation procedure with the help of a framework built with inputs from logistics experts. Fourth, the study recognises DTs adoption barriers in logistics management and provides a foundation for future research to eliminate those barriers.

This research explores the application of machine learning to optimize pricing strategies in the aftermarket sector, particularly focusing on parts with no assigned values and the detection of outliers. The study emphasizes the need to incorporate technical features to improve pricing accuracy and decision-making.

The methodology involves data collection from web scraping and backend sources, followed by data preprocessing, feature engineering and model selection to capture the technical attributes of parts. A Random Forest Regressor model is chosen and trained to predict prices, achieving a 76.14% accuracy rate.

The model demonstrates accurate price prediction for parts with no assigned values while remaining within an acceptable price range. Additionally, outliers representing extreme pricing scenarios are successfully identified and predicted within the acceptable range.

This research bridges the gap between industry practice and academic research by demonstrating the effectiveness of machine learning for aftermarket pricing optimization. It offers an approach to address the challenges of pricing parts without assigned values and identifying outliers, potentially leading to increased revenue, sharper pricing tactics and a competitive advantage for aftermarket companies.