• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Asia pacific journal of information systems
• /
• v.24 no.4
• /
• pp.559-575
• /
• 2014

Individual investors are increasingly flocking to message boards to seek, clarify, and exchange information. Businesses like Seekingalpha.com and business magazines like Fortune are evaluating, synthesizing, and reporting the comments made on message boards or blogs. In March of 2012, Yahoo! Finance Message Boards recorded 45 million unique visitors per month followed by AOL Money and Finance (19.8 million), and Google Finance (1.6 million) [McIntyre, 2012]. Previous studies in the finance literature suggest that online communities often provide more accurate information than analyst forecasts [Bagnoli et al., 1999; Clarkson et al., 2006]. Some studies empirically show that the volume of posts in online communities have a positive relationship with market activities (e.g., trading volumes) [Antweiler and Frank, 2004; Bagnoli et al., 1999; Das and Chen, 2007; Tumarkin and Whitelaw, 2001]. The findings indicate that information in online communities does impact investors' investment decisions and trading behaviors. However, research explicating the correlation between information on online communities and stock market activities (e.g., trading volume) is still evolving. Thus, it is important to ask whether a volume of posts on online communities influences trading volumes and whether trading volumes also influence these communities. Online stock message boards offer two different types of information, which can be explained using an economic and a psychological perspective. From a purely economic perspective, one would expect that stock message boards would have a beneficial effect, since they provide timely information at a much lower cost [Bagnoli et al., 1999; Clarkson et al., 2006; Birchler and Butler, 2007]. This indicates that information in stock message boards may provide valuable information investors can use to predict stock market activities and thus may use to make better investment decisions. On the other hand, psychological studies have shown that stock message boards may not necessarily make investors more informed. The related literature argues that confirmation bias causes investors to seek other investors with the same opinions on these stock message boards [Chen and Gu, 2009; Park et al., 2013]. For example, investors may want to share their painful investment experiences with others on stock message boards and are relieved to find they are not alone. In this case, the information on these stock message boards mainly reflects past experience or past information and not valuable and predictable information for market activities. This study thus investigates the two roles of stock message boards-providing valuable information to make future investment decisions or sharing past experiences that reflect mainly investors' painful or boastful stories. If stock message boards do provide valuable information for stock investment decisions, then investors will use this information and thereby influence stock market activities (e.g., trading volume). On the contrary, if investors made investment decisions and visit stock message boards later, they will mainly share their past experiences with others. In this case, past activities in the stock market will influence the stock message boards. These arguments indicate that there is a correlation between information posted on stock message boards and stock market activities. The previous literature has examined the impact of stock sentiments or the number of posts on stock market activities (e.g., trading volume, volatility, stock prices). However, the studies related to stock sentiments found it difficult to obtain significant results. It is not easy to identify useful information among the millions of posts, many of which can be just noise. As a result, the overall sentiments of stock message boards often carry little information for future stock movements [Das and Chen, 2001; Antweiler and Frank, 2004]. This study notes that as a dependent variable, trading volume is more reliable for capturing the effect of stock message board activities. The finance literature argues that trading volume is an indicator of stock price movements [Das et al., 2005; Das and Chen, 2007]. In this regard, this study investigates the correlation between a number of posts (information on stock message boards) and trading volume (stock market activity). We collected about 100,000 messages of 40 companies at KOSPI (Korea Composite Stock Price Index) from Paxnet, the most popular Korean online stock message board. The messages we collected were divided into in-trading and after-trading hours to examine the correlation between the numbers of posts and trading volumes in detail. Also we collected the volume of the stock of the 40 companies. The vector regression analysis and the granger causality test, 3SLS analysis were performed on our panel data sets. We found that the number of posts on online stock message boards is positively related to prior stock trade volume. Also, we found that the impact of the number of posts on stock trading volumes is not statistically significant. Also, we empirically showed the correlation between stock trading volumes and the number of posts on stock message boards. The results of this study contribute to the IS and finance literature in that we identified online stock message board's two roles. Also, this study suggests that stock trading managers should carefully monitor information on stock message boards to understand stock market activities in advance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.1-7
• /
• 2022

The purpose of this study is to discuss the impact of unmanned aerial vehicle service and how to activate it. The discussion on the impact of the introduction of the unmanned aerial vehicle service was examined in terms of economic, environmental, and social acceptance, and a plan to revitalize the industry was presented. In terms of economic impact, if transportation services are increased using unmanned aerial vehicles in the future, road-based transportation cargo may decrease and road movement speed may increase due to reduced road congestion. This can have a positive effect on the increase in the value of land or real estate assets, and it also provides an impact on smart city design. In terms of environmental impact, unmanned aerial vehicles (UAVs) generally move through electricity, so they emit less exhaust gas compared to other existing devices, such as vehicles and railroads, and thus have less environmental impact. However, noise can have a negative impact on the habitat in the presence of wild animals along their migration routes. In terms of social acceptability of unmanned aerial vehicles (UAV) technology, areas that are declining due to the emergence of new services may appear, and at the same time, organizations that create profits may appear, causing conflicts between industries. Therefore, it is essential to form a social consensus on the acceptance of emerging industries. The government should come up with various countermeasures to minimize the negative impact that reflects the characteristics of the unmanned aerial vehicle use service. Just as various systems such as road signs were introduced so that vehicles can be operated on the ground to secure air routes in the mid- to long-term for revitalization of unmanned-based industries, development and establishment of services that should be introduced and applied prior to constructing air routes I need this. In addition, the design and implementation of information collection and operation plans for unmanned air traffic management in Korea and a plan to secure a control system for each region should also be made. This study can contribute to providing ideas for mid- to long-term research on new areas with the development of the unmanned aerial vehicle industry.

• Journal of Global Scholars of Marketing Science
• /
• v.18 no.3
• /
• pp.89-114
• /
• 2008

Most of the extant studies on communication effects have been devoted to the typical issue, "what types of communication activities are more effective for brand awareness or brand attitudes?" However, little research has addressed another question on communication decisions, "what makes communication activities less effective?" Our study focuses on factors negatively influenced on the efficiency of communication activities, especially of Advertising. Some studies have introduced concepts closely related to our topic such as consumer confusion, brand confusion, or belief confusion. Studies on product belief confusion have found some factors misleading consumers to misunderstand the physical features of products. Studies on brand confusion have uncovered factors making consumers confused on brand names. Studies on advertising confusion have tested the effects of ad models' employed by many other firms for different products on communication efficiency. We address a new concept, Ad noises, which are any factors interfering with consumers exposed to a particular advertisement in understanding messages provided by advertisements. The objective of this study is to understand the effects of ad noises caused by ad models on brand awareness and brand attitude. There are many different types of AD noises. Particularly, we study the effects of AD noises generated from ad model selection decision. Many companies want to employ celebrities as AD models while the number of celebrities who command a high degree of public and media attention are limited. Inevitably, several firms have been adopting the same celebrities as their AD models for different products. If the same AD model is adopted for TV commercials for different products, consumers exposed to those TV commercials are likely to fail to be aware of the target brand due to interference of TV commercials, for other products, employing the same AD model. This is an ad noise caused by employing ad models who have been exposed to consumers in other advertisements, which is the first type of ad noises studied in this research. Another type of AD noises is related to the decision of AD model replacement for the same product advertising. Firms sometimes launch another TV commercial for the same products. Some firms employ the same AD model for the new TV commercial for the same product and other firms employ new AD models for the new TV commercials for the same product. The typical problem with the replacement of AD models is the possibility of interfering with consumers in understanding messages of the TV commercial due to the dissimilarity of the old and new AD models. We studied the effects of these two types of ad noises, which are the typical factors influencing on the effect of communication: (1) ad noises caused by employing ad models who have been exposed to consumers in other advertisements and (2) ad noises caused by changing ad models with different images for same products. First, we measure the negative influence of AD noises on brand awareness and attitudes, in order to provide the importance of studying AD noises. Furthermore, our study unveiled the mediating conditions(variables) which can increase or decrease the effects of ad noises on brand awareness and attitudes. We study the effects of three mediating variables for ad noises caused by employing ad models who have been exposed to consumers in other advertisements: (1) the fit between product image and AD model image, (2) similarity between AD model images in multiple TV commercials employing the same AD model, and (3) similarity between products of which TV commercial employed the same AD model. We analyze the effects of another three mediating variables for ad noises caused by changing ad models with different images for same products: (1) the fit of old and new AD models for the same product, (2) similarity between AD model images in old and new TV commercials for the same product, and (3) concept similarity between old and new TV commercials for the same product. We summarized the empirical results from a field survey as follows. The employment of ad models who have been used in advertisements for other products has negative effects on both brand awareness and attitudes. our empirical study shows that it is possible to reduce the negative effects of ad models used for other products by choosing ad models whose images are relevant to the images of target products for the advertisement, by requiring ad models of images which are different from those of ad models in other advertisements, or by choosing ad models who have been shown in advertisements for other products which are not similar to the target product. The change of ad models for the same product advertisement can positively influence on brand awareness but positively on brand attitudes. Furthermore, the effects of ad model change can be weakened or strengthened depending on the relevancy of new ad models, the similarity of previous and current ad models, and the consistency of the previous and current ad messages.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.