Future Sales Prediction For Indian Products Using Convolutional Neural Network-Long Short Term Memory

Kaunchi, Pooja; Jadhav, Tushar; Dandawate, Yogesh H.; Marathe, Pankaj

doi:10.1109/gcat52182.2021.9587668

Cited by 18 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors [18] also presented a hybrid model using CNN and the LSTM approach to forecast future sales for large-scale retailers. The authors used a dataset that included sales information for a range of products in India.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Sales Forecasting Using Convolution Neural Network

Wan Khairul Hazim Wan Khairul Amir,

Afiqah Bazlla Md Soom,

Aisyah Mat Jasin

et al. 2023

ARASET

View full text Add to dashboard Cite

Sales forecasting is an essential component of business management, providing insight into future sales and revenue. It is critical for effective inventory management, cash flow, and business growth planning. While many retailers rely on simple Excel functions or subjective guesses from management, the industry is increasingly turning to machine learning techniques to develop more accurate and reliable prediction models. Among these techniques, Convolutional Neural Networks (CNN) emerged as a suitable option due to their ability to learn and improve accuracy over time. CNN applies several layers to make predictions, adjusting their weights with each input data point to minimize prediction error. As a result, sales forecasting with neural networks can significantly improve market operations and productivity for businesses. The validity of the proposed model is compared with the Facebook Prophet method, which is known as the recent time series forecasting method.

show abstract

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Sales Forecasting Using Convolution Neural Network

Wan Khairul Hazim Wan Khairul Amir,

Afiqah Bazlla Md Soom,

Aisyah Mat Jasin

et al. 2023

ARASET

View full text Add to dashboard Cite

show abstract

“…[45] Uses LSTM with hyperparameters tuned with search grid optimization for predicting Walmart sales. Since the sales of the products like fashion clothes depend on the style and other similar attributes, [46] uses image features as parameters along with sales history data for predicting future sales.…”

Section: Comparative Study Of Deep Learning Modelsmentioning

confidence: 99%

A Comprehensive Study of Data Analytic Techniques for Sales Forecasting

2023

Recent Trends in Data Science and Its Applications

View full text Add to dashboard Cite

Predicting the sales of a product or demand for a service is an utmost need in any industry. With the changes and increase in the channels and modes through which the products are sold, the prediction of sales in the future becomes tedious. The number of features that would help in predicting sales differs and increases. This leads to the usage of Machine Learning and Deep Learning Models in sales forecasting. A deep survey of various works that employ machine learning and Deep learning approaches for sales prediction is done and inferences are made. Every work studied has a list of models which are used as baseline models for comparison and the same is listed for better inferences. Works that address the problem of predicting the sales of new products are also discussed. A list of publicly available sales forecasting datasets is also given.

show abstract

“…Long Short-Term Memory (LSTM) networks are a specific type of RNN architecture built to address the vanishing gradient problem, a common challenge faced by traditional RNNs in processing long sequences. LSTMs employ a gated memory cell that allows them to selectively store and access relevant information over longer periods, making them ideal for capturing the complex temporal dynamics of consumer behavior in ecommerce (Fischer & Krauss, 2018;Kaunchi et al, 2021;Yu et al, 2018). The proposed system goes beyond simple recommendation by integrating sophisticated time-series analysis to accommodate time-sensitive needs and transitions in product consumption stages.…”

Section: Introductionmentioning

confidence: 99%

Multidimensional Next-Generation Time and Transition-Aware Product Recommendation System

Ozpinar,

Mut

2024

EJRnD

View full text Add to dashboard Cite

In the dynamic landscape of e-commerce, the proliferation of products has immensely complicated the process of effective product discovery. With over 14 million items listed on platforms such as Pazarama.com, consumers often struggle to navigate through extensive catalogs to find products that genuinely meet their evolving needs. This challenge is exacerbated in categories requiring sequential consumption, such as baby products, where the progression from one product stage to another is not only inevitable but critical. Traditional recommendation systems primarily rely on static historical data. While these systems provide baseline suggestions based on past purchases or general popularity, they often fail to capture the nuanced and immediate requirements of consumers. For instance, a parent purchasing size one diapers will soon need to transition to size two, and a static system might continue to recommend size one, ignoring the child's growth. Moreover, these systems are not equipped to handle anomalies or data inconsistencies, often stemming from privacy regulations like the General Data Protection Regulation (GDPR), which can skew the effectiveness of the recommendations provided. This paper proposes a novel approach that integrates Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks to develop a multidimensional, next-generation product recommendation system. This system accommodates time-sensitive needs and transitions in consumer product stages, predicting future product requirements based on evolving consumer stages while handling anomalies and data inconsistencies due to privacy concerns. Furthermore, it offers real-time updates and integrates seamlessly with social media and online platforms to enhance user engagement and satisfaction. By employing time series analysis and advanced AI techniques, this model aims to improve the accuracy of personalized recommendations, support the introduction and marketing of new or rare products, and ultimately enhance the overall user experience on platforms like Pazarama.com. Through this approach, the paper demonstrates the potential for advanced recommendation systems to transform online retail environments by increasing sales, enhancing customer interaction, and expanding the technological repertoire of e-commerce platforms.

show abstract

Future Sales Prediction For Indian Products Using Convolutional Neural Network-Long Short Term Memory

Cited by 18 publications

References 13 publications

Sales Forecasting Using Convolution Neural Network

Sales Forecasting Using Convolution Neural Network

A Comprehensive Study of Data Analytic Techniques for Sales Forecasting

Multidimensional Next-Generation Time and Transition-Aware Product Recommendation System

Contact Info

Product

Resources

About