Customer Profiling Method with Big Data based on BDT and Clustering for Sales Prediction

Arai, Kohei; Ming, Zhan Ming; Fujikawa, Ikuya; Nakagawa, Yusuke; Momozaki, Tatsuya; Ogawa, Sayuri

doi:10.14569/ijacsa.2022.0130704

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper "Customer Profiling Method with Big Data based on BDT and Clustering for Sales Prediction" has been published, proposing and validating a method for sales prediction using big data [19]. Meanwhile, the paper "Modified Prophet+Optuna Prediction Method for Sales Estimations" has been published, also proposing and validating a prediction method for sales using actual sales data [20].…”

Section: Related Research Workmentioning

confidence: 99%

Method for Predictive Trend Analytics with SNS Information for Marketing

Arai,

Fujikawa,

Nakagawa

et al. 2024

IJACSA

View full text Add to dashboard Cite

A method for predictive trend analytics with social media information is proposed for marketing. Through keyword analysis, page view analysis, access analysis, heat map analysis, Google Analytics, real time analysis, company and competitor analysis, trend analysis with the social media data derived from X (former tweeter), Instagram, Facebook, YouTube, TikTok, market trend can be predicted. The proposed method is created in a local server and is extended to AWS cloud. The proposed system, also ensure negative / positive analysis from the acquired social media information. Through some experiments, it is found that by using AI to analyze social data by category, you can visualize the degree of attention for each keyword, model relationships between information, identify trending keywords, and where the keywords are in their lifecycle. It turns out that it's possible to categorize which ones exist and predict which ones will scale up in the next six months. In addition, corporate product development and marketing personnel can identify themes, materials, benefits, etc. that have signs of becoming popular based on insights based on predictive behavioral data obtained from the proposed method and system and utilize them in new business development and new product planning.

show abstract

Section: Related Research Workmentioning

confidence: 99%

Method for Predictive Trend Analytics with SNS Information for Marketing

Arai,

Fujikawa,

Nakagawa

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Customer profiling method with Big Data based on Binary Decision Tree: BDT and clustering for sales prediction is proposed and tested with POS: Point of Sales data [20]. Furthermore, a modified Prophet+Optuna prediction method for sales estimations is also proposed [21].…”

Section: • No Need To Impute Missing Valuesmentioning

confidence: 99%

Churn Customer Estimation Method based on LightGBM for Improving Sales

Arai¹,

Fujikawa²,

Nakagawa³

et al. 2023

IJACSA

View full text Add to dashboard Cite

Churn customer estimation method is proposed for improving sales. By analyzing the differences between customers who churn and customers who do not churn (returning), we will conduct a customer churn analysis to reduce customer churn and take steps to reduce the number of unique customers. By predicting customers who are likely to defect using decision tree models such as LightGBM, which is a machine learning method, and logistic regression, we will discover important feature values in prediction and utilize the knowledge obtained through Exploratory Data Analysis (EDA). As results for experiments, it is found that the proposed method allows estimation and prediction of churn customers as well as characteristics and behavior of churn customers. Also, it is found that the proposed method is superior to the conventional method, GradientBoostingClassifier (GBC) by around 10%.

show abstract

Customer Profiling Method with Big Data based on BDT and Clustering for Sales Prediction

Cited by 2 publications

References 12 publications

Method for Predictive Trend Analytics with SNS Information for Marketing

Method for Predictive Trend Analytics with SNS Information for Marketing

Churn Customer Estimation Method based on LightGBM for Improving Sales

Contact Info

Product

Resources

About