A Predictive Analysis of the Indian FMCG Sector Using Time Series Decomposition-Based Approach

Abstract

Abstract. Stock price movements being random in its nature, prediction of stock prices using time series analysis presents a very difficult and challenging problem to the research community. However, over the last decade, due to rapid development and evolution of sophisticated algorithms for complex statistical analysis of large volume of time series data, and availability of high-performance hardware and parallel computing architecture, it has become possible to efficiently process and effectively analyze voluminous and highly diverse stock market time series data effectively, in real-time. Robust predictive models are being built for accurate forecasting of values of highly random variables such as stock price movements. This paper has presented a highly reliable and accurate forecasting framework for predicting the time series index values of the fast moving consumer goods (FMCG) sector in India. A time series decomposition approach is followed to understand the behavior of the FMCG sector time series for the period January 2010 till December 2016. Based on the structural analysis of the time series, six methods of forecast are designed. These methods are applied to predict the time series index values for the months of 2016. Extensive results are presented to demonstrate the effectiveness ofthe proposed decomposition approaches of time series and the efficiency of the six forecasting methods.

A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing

“…c) day_week: it is a numeric variable that refers to the day of the week corresponding to a given record. This variable lies in the range [1,5]. Monday is coded as 1, while Friday is coded as 5. d) close_norm: it is a numeric variable that is computed as a standardized value of the percentage change in the Close prices on two successive days.…”

Design and Analysis of Robust Deep Learning Models for Stock Price Prediction

“…Hence, quite often, these models do not yield an acceptable level of accuracy in prediction. Autoregressive integrated moving average (ARIMA) and other approaches of econometrics such as cointegration, vector autoregression (VAR), causality tests, and quantile regression (QR), are some of the methods which fall under the second category of propositions [5][6][7][8][9][10][11][12][13][14][15][16]. The methods of this category are superior to the simple regression-based methods.…”

“…The study conducted by the authors reveals two significant findings: (i) higher accuracy is achieved by models involving fewer parameters, and (ii) the daily return values exhibit a strong autoregressive property. Sen and Datta Chaudhuri different sectors of the Indian stock market using a time series decomposition approach and predict the future stock prices using different types of ARIMA and regression models [9][10][11][12][13][14]33]. Zhong and Enke present a gamut of econometric and statistical models, including ARIMA, generalized autoregressive conditional heteroscedasticity (GARCH), smoothing transition autoregressive (STAR), linear and quadratic discriminant analysis [16].…”

Talaşlı İmalat Sektöründe Zaman Serileri Kullanarak Üretim Etkililiğinin Tahmini

“…Bunun yanında Hindistan hızlı tüketim malları sektöründe zaman serisi tabanlı tahmin analizi gerçekleştirmiştir. Çalışma da AR, MA, ARIMA, PACF (Partial Auto Correlation Function) ve ACF (Auto Correlation Function) yöntemleri karşılaştırılmıştır [15]. Kaynar 2009 yılında aylık ve günlük döviz kurları üzerinden zaman serisi analizinde yapay sinir ağları ve ARIMA modellerini karşılaştırmıştır [6].…”

“…AR (Auto Regressive) model, bir modelin çıktısını, bir önceki değere bakarak lineer olarak, stokastik fark denklemi olarak verir. Bir AR modelinde, bağımlı değişken geçmişteki değerinin bir fonksiyonudur[15]. Bu durum aşağıdaki gibi bir denklemle ifade edilmektedir.Yt = c + a1Yt-1 + a2Yt-2 • • • + apYt-p + ut Yt: t anındaki sonuç değişkeni Y t− 1 , Y t− 2 ,...,Y t− p = Sırasıyla t − 1,t − 2,...ut, ut-1,ut-2,...,ut-q: Hata terimleri AR ve MA modelleri bir araya gelerek daha karmaşık stokastik yapılara sahip olan ARIMA yöntemlerini meydana getirirler.…”