Selling Decisions Research Articles

RETRACTED: Machine learning-based probabilistic profitable model in algorithmic trading

Machine learning models are nowadays becoming ubiquitous in algorithmic trading and investment management. These models are mostly used in the pre-trade analysis phase to determine the buy or sell decisions using various machine learning techniques. We aim to implement a machine learning-driven approach using various technical indicators to predict stock market prices and then accordingly make a decision about buying or selling. First, an effective trading strategy is discussed that selects the potentially profitable stocks, and then the technical indicators such as simple moving average (SMA), exponential moving average (EMA), relative strength index (RSI), and moving average convergence divergence (MACD) are calculated for those potentially profitable stocks. Then supervised machine learning algorithms such as multiple linear regression, support vector machine regression, and decision tree regression are applied, where the close price of the stock is predicted using technical indicators for the next day, and based on that buy or sell signals are generated. The model is then tested on 12 different SNP500 stocks, one for every month in 2018, with the mean squared error (MSE) varying between 30.33 and 48.16 and the root MSE varying between 5.51 and 6.93, where the error is calculated on the difference in the number of days when the stock price actually increases and the predicted number of days for various models.

Covid-19 - Pushes Marketers To Sell Differently To Global Millennials In Emerging Markets

‘CoronaVirus’ is a hard hit on both Millennial consumers and marketers. It forced consumers and marketers to do the usual activities of buying and selling differently. Panic buying and herd mentality was widely noticed among millennials. Their unusual buying behavior which reflects behavior during a crisis is highly influenced by environmental stimuli. From this study, it is found that there has been a significant buying behavioral shift of global millennials in emerging markets (BRIC – Brazil, Russia, India, China; CIVETS – Columbia, Indonesia, Vietnam, Egypt, Turkey, South Africa). It is evident that the initial marketing attempts of marketers failed during COVID-19 due to the lack of understanding of the significance of environmental and marketing stimuli in consumers’ purchase decisions. This study brings out the various positive substantial changes brought about through internetization in marketing goods and services to millennial customers during the pandemic. The pandemic enabled a rapid digital revolution in buying and selling using digital/online platforms. The study suggests the application of the Black Box Model by marketers in marketing and selling decisions. The Internet has been the most important tool used by customers and sellers to access what they need. This study is useful to marketers and upcoming entrepreneurs to understand that it is the consumer’s buying behavior that triggers and pushes marketers to sell differently.

Commission, product quality and return policy in agency selling

AbstractMany sellers provide products for consumers directly on online platforms. This selling format is labeled “agency selling.” In this article, we investigate the platform's contract design and the seller's quality and return decisions in the agency selling. We find that the platform chooses a high commission rate to induce the seller to accept returns when the salvage factor is large enough or the consumers' willingness to pay for quality is sufficiently low. Compared to the direct channel, the seller is more likely to accept returns in the agency selling. Moreover, if the consumers' willingness to pay for quality increases, the platform intends to reduce the commission rate to induce the seller to increase the quality. The commission rate makes no influence on the generosity of the refund. However, when the consumers' willingness to pay for quality is sufficiently large, the platform prefers the seller to offer no refund and the commission rate may increase in the consumers' willingness to pay for quality. Finally, we consider two extensions: quality affects satisfaction probability and return window.

Strategic Business Mode Choices for E-Commerce Platforms under Brand Competition

Relying on the rapid development of information and internet technologies, e-commerce has boomed over the past decade. As a link between manufacturers and consumers, the e-commerce platform has a crucial position in the online retailing market. The e-commerce platform not only provides an online marketplace through which the manufacturers directly sell products to consumers but also purchases and resells manufacturers’ products to consumers. Therefore, when the e-commerce platform provides services to manufacturers, it is faced with the selection of two sales methods: reselling or marketplace. Using a game theoretic model, we focus on the strategic interactions between an e-commerce platform and two brand manufacturers in four different business modes. The results show that the e-commerce platform profits more when both brand manufacturers directly sell products through the online marketplace. From the two brand manufacturers’ points of view, using the e-commerce platform as a reseller is always more profitable than directly selling, no matter which business mode they are in. The above findings have important implications for the selling decisions of the e-commerce platform and brand manufacturers. Furthermore, an interesting and counterintuitive result is that the new brand manufacturer benefits more than the existing brand manufacturer when consumers’ acceptance of the new brand products is becoming lower. When production costs are low, only the two brand manufacturers can achieve a mutually beneficial situation by selling products to the e-commerce platform. Moreover, the competition among brand manufacturers is beneficial to the e-commerce platform. Our research provides a theoretical basis for brand manufacturers and the e-commerce platform to make more rational decisions, and it updates the existing knowledge about brand competition and e-commerce platform’s business mode choices.

Tokat İli İkinci El Pazarındaki Traktörlerin Teknik ve Ekonomik Özelliklerinin Belirlenmesi

In this study, it is aimed to determine the technical and economical specifications of the used tractors put to sale in Tokat province and its districts, such as rated engine power, age, usage hours, tractor structure, maintenance and repair requirements and sale price. Also, it is intended to reveal the tendencies of farmers in tractor demand. The technical and economical specifications of used tractors in the second-hand tractor market in Tokat province and its districts has been analysed. For this purpose, all data has been collected from tractor owners through face-to-face interviews for a total of 408 tractors in 7 districts. According to the data, generally the tractors are standard type, and their age range is between 1 and 58. Based on the data collected from tractor owners, the average annual usage time of the tractors for Tokat is 268 hours, and the average rated power is 58.5 HP (43.6 kW). The remarkable sale reasons of used tractors are model obsolescence, insufficient capacity and need for cash respectively. In the second-hand tractor market, the age of the tractors, rated engine power, brand, usage hours and other technical specifications are primarily factors about pricing. Although 41% of the tractors in the sale have almost completed their lifespan, it has been determined that they can be preferred to some extent. It has been also revealed that tractors with very good service network and tractors that tractor owners can find buyers with the price that they want to sale are most common tractor types in the market. In addition, it is thought that the farmers’ awareness should be developed because they tend to make unconscious buying and selling decisions.

Chaotic Bi-LSTM and attention HLCO predictor-based quantum price level fuzzy logic trading system

There are various indicators, i.e., Relative Strength Index (RSI) [1] [2], Moving Average Convergence Divergence (MACD) [3] [4] [5] [6], Stochastic Oscillator [7] [8] applications, to determine market movements with buying and selling decisions in computational Finance, but they have drawbacks that induced discrepancies to match against the best trading times at fixed order-triggering boundaries and delay problems. For example, RSI [1] [2]’s 70 and 30 overbuy and oversell are fixed boundaries. Orders can only be triggered when RSI’s value exceeds one of these boundaries, its computation only considers past market condition prompting indicators like RSI to trigger orders with delay. In this paper, we proposed a method to reduce these problems with advanced AI technologies to generate indicators’ buy and sell signals in the best trading time. Recurrent Neural Network (RNN) [9] has outstanding performance to learn time-series data automatic with long-time sequences but its ordinary RNN units [10] [11] such as Long-Short-Term-Memory(LSTM)[12] are unable to decipher the relationships between time units called context. Hence, researchers have proposed an algorithm based on RNNs’ Attention Mechanism [13] [14] allowing RNNs to learn information such as chaotic attributes [15] [16] [17] [18] and Quantum properties [19] [20] [21] contained in time sequences. Chaos Theory [15] [16] and Quantum Finance Theory (QFT) [22] are also proposed to simulate these two features (or attributes?). Quantum Price Level (QPL) [22] [23] is one of the well-formed QFT models to simulate all possible vibration levels to locate price. The system used in this paper consists of two components 1) neural network to predict future data and solve indicators lagging problem, and 2) fuzzy logic to solve fixed order-triggering boundaries problem. Its system design has two main parts 1) Chaotic HLCO Predictor consists of LSTM, Lee-Oscillator and attention mechanism to predict the High, Low, Close and Open, 2) QPL-based Fuzzy Logic Trading Strategy to receive the result and trigger trading signals. This new proposed model has obtained significant results in backtesting previous data and outperformed other traditional indicators to facilitate investment decisions when market changes constantly. Codes are available at https://github.com/JarvisLee0423/ Chaotic Quantum Finance AI Predicted Trading System.

MODELING STOCK-CLOSING PRICES: EVIDENCE FROM THE BANKING SECTOR OF JORDAN

This study aims to find the best-fitted distribution of the average closing price (ACP) for the Amman Stock Exchange banking sector using various distributions models, namely, Normal, Gamma, Burr, Weibull, Bareto, lognormal, Log logistic, Exponential, and Gumbel distribution. This will enable financial analysts to forecast stock prices to build their buying and selling decisions. The methodology was applied according to the comparison between maximum likelihood estimation, moment matching, quantile matching and maximum goodness-of-fit estimation. The result of computing the different goodness of fit statistics (K.S), (CvM) and (A.D) and the other statistics based on the log-likelihood (AIC and BIC). The best-fitted distributions have the smaller values for each goodness of fit statistics. The results emphasized that the Gamma distribution is the most appropriate one, which has the lowest values of AIC (364.6), and BIC (373.9).

Indebted sellers, liquidity and mortgage standards

The effects of households’ indebtedness on their house selling decisions, the implications of these decisions for default and the effects of policies intended to reduce the incentive to default are studied in a dynamic model with search in the housing market and defaultable long-term mortgages. In equilibrium, both sellers’ asking prices and time-to-sell increase with the relative size of their outstanding debt. For sellers in financial distress, this behavior results in a positive relationship between debt and their individual risk of default. Prices and time-to-sell determine both the liquidity of the housing market and the aggregate risk of default. As such they determine the extent of profitable lending by competitive lenders. Calibrated to the U.S. economy, the model also generates, as observed, positive correlations (i) across sellers of asking prices with loan-to-value ratios, and (ii) over time of both house prices and time-to-sell with mortgage loan-to-value ratios at mortgage origination. Policies aimed at reducing default may be counterproductive if they raise the value of mortgages and thus lower lending standards, ultimately increasing the rate of default and reducing aggregate welfare. We consider also the implications of these policies for the effects of aggregate shocks on house prices and the rate and severity of mortgage default.

Intuitionistic fuzzy rule-base evidential reasoning with application to the currency trading system on the Forex market

In this paper, the application of the intuitionistic fuzzy rule-base evidential reasoning (IFRBER) to the development of a new optimized automated trading system (ATS) for the Forex market is presented. The used IFRBER approach represents the intuitionistic fuzzy sets in the framework of the evidence theory that allows us to avoid the revealed drawbacks of the IFS operational laws and enhance the overall performance of the IFRBER approach. It is shown that the IFRBER approach extracts from an analyzed system considerably more of useful for the decision making information than the usual fuzzy rule-base evidential reasoning (FRBER). Then based on the IFRBER, a new approach to make the justified transaction buying and selling decisions was proposed. This approach was used to develop a new optimized ATS for the Forex market. It is shown that due to the ability of a new approach to use more of useful information that present implicitly in the problem formulation than the proposed earlier usual fuzzy rule-base evidential reasoning method, the developed ATS provides a considerably more profitable and comfortable (with a higher percent of winning trades and with low risks) trading than the earlier developed ATS.

Congestion tolling — Dollars versus tokens: Within-day dynamics

Tradable credit schemes (or tolling in tokens) are a form of quantity control, which promise to be an appealing alternative to congestion pricing (or tolling in dollars) owing to considerations of revenue neutrality, equity, reduced infrastructure costs, and political acceptability. The comparative performance of the two instruments under uncertainty in demand and supply has only recently received attention in the transportation setting, despite being widely studied for emission markets. In this paper, we add to this literature by considering a tradable credit scheme in a departure time context wherein users are provided an initial endowment of tokens by the regulator and incur a token charge (determined prior to all departures) to travel in a specific time-period. Tokens can be bought and sold within a marketplace at a price determined endogenously by token demand and supply. Two key features of the market model are: (1) the time-of-day dynamics of price is explicitly modeled through a smooth market clearing mechanism in each period, and (2) the selling decisions of users, which determine the distribution of token supply in the market over the day are explicitly modeled. This enables us to study the impact of selling behavior on performance of the credit system. Travel demand is modeled using a logit mixture model and supply consists of static congestion.Extensive experiments under stochastic demand show that when the tolls (in dollars and tokens) are not day-to-day adaptive, tolling in tokens outperforms tolling in dollars when congestion effects are more severe (e.g., realistic BPR models and steep congestion functions, high demand levels and high day-to-day variability). Importantly, we find that this result is robust with respect to selling behavior in the market, although there can be welfare losses in the quantity control system when selling behavior in the market is excessively irrational. These findings underscore the importance of examining disaggregate market behavior when designing tradable credit schemes. Moreover, when the supply of tokens can be adapted from day to day, the credit system was found to be superior in all tested scenarios, provided the selling behavior of individuals is rational. Finally, even in the case when toll revenues in the price instrument are equally redistributed (often difficult in practice), tolling in tokens (when tokens are equally distributed) is marginally more equitable in scenarios where congestion effects are more severe. These findings make a case for tolling in tokens.

Trend following or reversal: Does culture affect predictions and trading behavior?

We investigate cross-cultural differences in forecasting stock markets and trading tendencies using a survey sample of 339 participants from Switzerland, Ukraine, and China. We find that (1) subjects in all countries exhibit representative bias but in different directions. The Swiss tend to extrapolate recent trends, whereas the Chinese tend to predict reversals. This result is consistent with previous research on cultural lay theories of change. Ukrainian students tend to be optimistic in both up and down markets. (2) Swiss students tend to provide a wider confidence interval in their forecasts than Chinese and Ukrainian students. (3) Subjects from all three countries make similar selling decisions and exhibit the disposition effect, i.e., selling winning stocks while holding losing ones. (4) Concerning buying decisions, Swiss and Chinese students are trend followers. In contrast, Ukrainian students are more likely to buy in both bear and bull markets, perhaps driven by their optimistic view of the future. We did not find a uniform pattern across countries for gender differences in forecast intervals and decision confidence.

Private Equity and Family Firms - Barbarians on the Yard: A Vignette Study

External succession through the private equity route has recently become a more common option for family firms. Drawing on the socioemotional wealth (SEW) perspective, we study what factors influence the selling decision of family firm owners and managers and look at the moderating role of family firm portfolios. Based on a unique vignette study conducted with 200 vignette responses by family firm owners and managers, we unveil that levels of SEW and financial performance influence the propensity to sell. Surprisingly, the existence of family firm portfolios only significantly moderates the relationship between innovation performance and the propensity to sell. Our research provides important implications for research on family firm external succession and the SEW literature, contributing insights on the factors influencing decisions on the private equity succession route

Trading Prediction Model and Strategy Formulation Based on Grey System

In this paper, we study the optimal investment strategy between gold and Bitcoin, establish a market price forecasting system using the grey forecasting model GM (1,1), and calculate the optimal investment between gold and Bitcoin through the association rule algorithm. Optimal investment ratio, and then determine the maximum return. The establishment of predictive investment models helps investors to formulate optimal investment plans. The established model can use certain data from previous years to predict the future exchange rate prices of gold and bitcoin and help trading investors make optimal buying and selling decisions. It has a certain model planning ability for investment in real life and has specific practical significance for trade investors.

Impact of Price Path on Disposition Bias

Recent experimental studies illustrate the influence of price path, particularly the ‘non-straight’ price path, on several aspects of investor decision-making. The paper employs an empirical proxy for price path based on convexity and demonstrates that price convexity significantly impacts the selling decisions with transaction-level data. We find that a price path that is likely to signal a favourable (unfavourable) price movement in the future lowers (heightens) the selling propensity of traders in stocks. The findings suggest that likely expectations about future price movement, as could be inferred from the experienced price path, significantly influence the trading decisions of retail traders.

Stock Market Prediction using Deep Learning

Abstract: Stock market is very uncertain and highly volatile as the prices of stocks keep fluctuating due to several factors that make prediction of stocks a very difficult and complicated task. In the finance and trading world stock analysis and trading is a method for investors and traders to make buying and selling decisions. Investors and traders try to gain an edge in the markets by taking informed decisions by studying and evaluating past and current data. Stock market prediction has always been an important research topic in the financial and trading field [2]. Prediction of stock market is the act of trying to determine the future value of a company stock (nifty & sensex) or other financial instrument traded on an exchange. Our project explains the prediction of a stock using Machine Learning, which itself employs different models to make prediction easier and authentic. The paper focuses on the use of Recurrent Neural Networks (RNN) called Long Short Term Memory (LSTM) to predict stock values. This will help us provide more accurate results when compared to existing stock price prediction algorithms. The eminent analysis of the stock will be an asset for the stock market investors and will provide real-life solutions to the problems and also yield significant profit. Keywords: Stock Price Prediction, Machine Learning, Long Short-Term Memory, Recurrent Neural Networks

A Hybrid Machine Learning Technique for Stork Market Prices Prediction

Stock markets in financial domain play crucial role in economy of nations in the contemporary world. There are many stakeholders who depend on the prediction of stock prices for making buying and selling decisions. In this context, it became important to deal with automatic stock prices prediction. Since manual observation is not possible, machine learning (ML) techniques are widely used for prediction of stock prices movement. Many ML algorithms came into existence. However, their performance largely depends on the quality of training data as they are based on unsupervised learning. In this paper, a hybrid ML framework is proposed to have both feature selections to improve quality of training and the leveraging forecasting performance. The proposed framework supports different techniques such as Linear Regression, XG Boost Regression and Gradient Boost. A prototype application is built using Python data science platform. Experimental results revealed that the three prediction models are providing high level of accuracy. Linear Regression showed 99.989% accuracy, GBoost regression 99.981 and XGBoost Reggressor 0.99969. From the results, it is ascertained that the proposed framework is useful for efficient forecasting of stock prices movements. Keywords – Stock Market Prediction, Machine Learning, Linear Regression, GBoost Regression, XGBoost Reggressor

Joint Ordering and Selling Policy for Storable Agricultural Products in Contract Farming

With the farming mode widely promoted in many countries around the world, agricultural enterprises need to face risks from both supply and sales at the same time. Especially for storable agricultural products, it is also necessary to consider the potential profits and losses brought about by the sales of multi-period. This paper establishes a joint ordering and selling decision model under multiperiod random supply and demand. The model takes the maximum expected profit of agricultural enterprises as the goal, considers the constraints of production capacity and the risk preference coefficient of shortage, and makes decisions on the order and sales quantity in each cycle. The feasibility of the model was verified by taking China Yunnan Pu’er tea as a specific example. Finally, through numerical examples, the influence of important parameters on the joint ordering and selling strategy is as follows: order cost is the main factor affecting the order quantity. When the order cost increases to a certain level, the solving algorithm will make a decision that would rather be out of stock than to order. With the increase in selling price, inventory holding cost, and shortage cost, there will be an increasing trend of the sales quantity allocated to this period. Compared with other parameters, selling price and inventory holding cost have a more remarkable impact on sales quantity. In addition, enterprises can increase their expected profits of storable agricultural products by controlling the inventory holding cost, appropriately reducing the risk preference coefficient, and increasing the level of the selling price.

Managing the exchange of energy between microgrid elements based on multi-objective enhanced marine predators algorithm

Optimal planning for the energy storage elements’ status of charging and discharging, besides managing the buying and selling energy from the grid, is the first step for enhancing energy usage and saving costs for customers. Therefore, in this work, an enhanced multi-objective optimization algorithm of the Marine Predators Algorithm (MOEMPA) is proposed to handle three objective functions for minimizing the operating cost and emission with maximizing the renewable factor for optimal usage of the energy resources. The proposed MOEMPA is applied for managing the sharing energy in an interconnected microgrid with utility grid. The considered microgrid consists of solar and wind renewable energy sources, diesel for emergence loads, and set of batteries for storage extra energy. The described system used for feeding the required power under three different cases for the weather and the grid continuity/discontinuity along 96 h horizon in India, Delhi. The proposed MOEMPA results are compared with recent multi-objective optimization algorithms including, basic variant of multi-objective versions of marine predators algorithm (MOMPA), grasshopper optimization algorithm (MOGOA), slime mould algorithm (MOSMA), grey wolf optimizer(MOGWO), antlion optimizer (MOALO), and multi-verse optimizer (MOMVO) to assess the performance of the proposed scheduled system based MOEMPA. Furthermore, the baseline system is implemented to provide a comprehensive evaluation for the proposed approach based on MOEMPA. The comparisons and analyses reveal the efficacy and excellence of the proposed approach in minimizing the cost and emission with enhancing the profit for the customers via providing an the optimal managing between staging, discharging, buying, and selling decisions. The analysis affirms that, the scheduled system based on MOEMPA has the highest cost-saving of 16.0%, 34.5%, and 26.9% compared with the baseline schedule and other peers over the studied scenarios of operation. Moreover, the schedules based on MOEMPA reduced the emissions by 13.37 % and 14.7%. For the renewable factor, the scheduled system based on MOEMPA enhanced its values to 69.3% and 36.6%; meanwhile, the baseline system has 73.4% and 25.9%, hence the proposed approach guarantee feeding the load with high profit.

Rent, sell, and remanufacture: The manufacturer's choice when remanufacturing can be outsourced

Manufacturers have increasingly started offering rental options for the products they sell. Renting products offers an opportunity: segmenting consumers. However, this also raises a challenge: what to do with the returned products? One solution is to remanufacture these products and then rent or resell them. Subsequently, should remanufacturing be outsourced to a third-party firm that can remanufacture at a lower cost? Here, we use a multi-period setting and examine the optimal decisions for different selling and renting constellations. Importantly, we allow the manufacturing costs of the sales and rental products to differ, as they seem to be critical in determining the manufacturer's renting and selling decisions and remanufacturing strategies. For example, under integrated (i.e. in-house) remanufacturing, when the new rental product's manufacturing cost is sufficiently high, no remanufacturing happens. Under both remanufacturing strategies—integrated and outsourced—the manufacturer does not rent new products in the second period if the manufacturing costs of the sales and rental products are identical. If the rental product's manufacturing cost is either sufficiently low or high, then integrated remanufacturing is more profitable; when this manufacturing cost is within a moderate range, the manufacturer outsources remanufacturing to an independent remanufacturer. Surprisingly, in some situations, the production quantity of the new sales product may even increase with its manufacturing cost. This is because the manufacturer may extract an even higher margin compared with the new rental product. Finally, we also consider several extensions such as uncertainty regarding the quality of the returned goods, simultaneous selling and renting of remanufactured goods, and longer horizons and the product's life cycle.

On Feedforward Stock Trading Control Using a New Transaction Level Price Trend Model

In this article, we provide a new Markovian-type model for stock price trend analysis at the transaction level, and illustrate its use for trading in conjunction with a controller, which makes buy and sell decisions. Central to our formulation is a sequence of i.i.d. random variables <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$T_k$</tex-math></inline-formula> , which corresponds to the number of transactions between reversals in price direction. For a trader, this is an important indicator of the “duration” of a trend. For processes with “large” <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$T_k$</tex-math></inline-formula> , there is an incentive to try and capitalize by buying stock when a temporary trend is “up” and selling when it is “down.” The extent to which this is possible is determined by a model parameter <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$p_e$</tex-math></inline-formula> , called the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">probability of efficiency</i> , which indicates the likelihood that the bid, ask, and current price are such that one can seamlessly enter or exit the market without slippage. The degree to which a trader can exploit trending behavior is quantified in our main result, which provides the expected value of the trading gain resulting from a strategically constructed feedforward switching controller. This article also includes an example illustrating application of the theory using historical data.